The rise and potential of large language model based agents: a survey
Open accessThe DOI matches its Crossref record; 704 of the 704 references it cites were found in a registry or an index.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“LLM-based agents couple large language models with planning, memory retrieval, tool invocation and execution, enabling temporally extended, partially autonomous collaboration [1-3].”
From Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration (2026) · cites this paper as [3]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“NoD adds a related lesson: operator assumptions about reachability, path selection, and service access must also be checked, since mismatches can expose policy gaps and security risks [52].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [52]
Experimental — accuracy not yet measuredIn the citing paper
“LLM-based autonomous agents can achieve greater flexibility and robustness by dividing labor among sub-agents [1,3].”
From A Review of Multi-Agent AI Systems for Biological and Clinical Data Analysis (2026) · cites this paper as [3]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Items 401–600 of 704
Ribeiro, C. H. C. (2002) · Artificial Intelligence Review · doi:10.1023/a:1015008417172 · Cited by 85 · cited 1×
“…capabilities and data availability, along with a growing interest in simulating interactions between intelligent agents and their environments, researchers have begun to utilize reinforcement learning methods to train agents for tackling more challenging and complex tasks [11,12,44,45].”
Implicit Representations of Meaning in Neural Language Models
Li, B. Z., Nye, M., & Andreas, J. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.143 · Cited by 84 · cited 1×
“Although intuitively the paradigm of next token prediction in LLMs may not possess intention or desire, research has shown that they can implicitly generate representations of these states and guide the model’s inference process [105–107].”
An Exploration of Hierarchical Attention Transformers for Efficient Long Document ClassificationPreprint
Chalkidis, I., Dai, X., Fergadiotis, M., Malakasiotis, P., & Elliott, D. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.05529 · Cited by 84
Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision
Du, W., Kim, Z. M., Raheja, V., Kumar, D., & Kang, D. (2022) · Workshop on Intelligent and Interactive Writing Assistants (In2Writing) · doi:10.18653/v1/2022.in2writing-1.14 · Cited by 83
Social Science Microsimulation
Troitzsch, K. G., Mueller, U., Gilbert, N., & Doran, J. (1996) · Springer eBooks · doi:10.1007/978-3-662-03261-9 · Cited by 83
OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization
Iyer, S., Lin, X. V., Pasunuru, R., Mihaylov, T., Simig, D., Yu, P., Shuster, K., Wang, T., Liu, Q., Koura, P. S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.12017 · Cited by 81 · cited 1×
“Promisingly, such generalization capability can be further enhanced by scaling up the model size and the quantity or diversity of training instructions [75,185].”
Self-citationChatDev: Communicative Agents for Software Development
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.07924 · Cited by 81
Self-citationVing: Learning open-world navigation with visual goals
Shah, D., Eysenbach, B., Kahn, G., Rhinehart, N., & Levine, S. (2021) · 2021 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48506.2021.9561936 · Cited by 81
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Shridhar, M., Yuan, X., Côté, M.-A., Bisk, Y., Trischler, A., & Hausknecht, M. (2020) · arXiv · doi:10.48550/arxiv.2010.03768 · Cited by 80 · cited 1×
“…virtual simulation environments and the real physical world: Virtual environments are scenes-constrained, task-specific, and interacted with in a simulated manner [292,563], while real-world environments are boundless, accommodate a wide range of tasks, and interact with in a physical manner.”
Learning to Model the World with LanguagePreprint
Lin, J., Du, Y., Watkins, O., Hafner, D., Abbeel, P., Klein, D., & Dragan, A. D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.01399 · Cited by 80 · cited 1×
“However, caption generation is a low-bandwidth method [101,208], and it may lose a lot of potential information during the conversion process.”
Formalizing Properties of Agents
GOODWIN, R. (1995) · Journal of Logic and Computation · doi:10.1093/logcom/5.6.763 · Cited by 79 · cited 3×
“As previously mentioned, AI agents must possess the ability to perceive their environment, make decisions, and carry out actions effectively [3,31].”
InfluentialCross-modal Map Learning for Vision and Language Navigation
Georgakis, G., Schmeckpeper, K., Wanchoo, K., Dan, S., Miltsakaki, E., Roth, D., & Daniilidis, K. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01502 · Cited by 79 · cited 1×
“Some studies [275, 276] highlighted the importance of spatial representation to obtain the precise localization of targets by leveraging the pre-trained VLM model to combine visual features from images with 3D reconstructions of the physical world [250].”
Multi-Party Chat: Conversational Agents in Group Settings with Humans and ModelsPreprint
Wei, J., Shuster, K., Szlam, A. D., Weston, J., Urbanek, J., & Komeili, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.13835 · Cited by 79
AgentBench: Evaluating LLMs as Agents
Liu, X., Yu, H., Zhang, H., Xu, Y., Lei, X., Lai, H., Gu, Y., Ding, H., Men, K., Yang, K., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.03688 · Cited by 79 · cited 2×
“Effectively and objectively evaluating LLMs agents presents significant challenges, despite their excellent performance in areas such as standalone operation, collective cooperation, and human interaction [70,484].”
Self-citationBounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints
Lu, A., Zhang, H., Zhang, Y., Wang, X., & Yang, D. (2023) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2023.findings-eacl.148 · Cited by 78
Self-citationAn empirical investigation of the challenges of real-world reinforcement learning
Dulac-Arnold, G., Levine, N., Mankowitz, D. J., Li, J., Paduraru, C., Gowal, S., & Hester, T. (2020) · arXiv · doi:10.48550/arxiv.2003.11881 · Cited by 78
DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving AgentsPreprint
Nair, V., Schumacher, E., Tso, G., et al. (2023) · Clinical Natural Language Processing Workshop · doi:10.48550/arxiv.2303.17071 · Cited by 75 · cited 2×
“This includes enhancing decision-making in traditional agent frameworks, and potentially transforming domains previously dominated by human experts, like legal consultation and medical assistance [326,330].”
Choi, M., Pei, J., Kumar, S., Shu, C., & Jurgens, D. (2023) · arXiv · doi:10.48550/arxiv.2305.14938 · Cited by 73
Minsky, M., & Forum, T. P. (1987) · The Personalist Forum · doi:10.5840/persforum19873112 · Cited by 73
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Fan, L., Wang, G., Jiang, Y., Mandlekar, A., Yang, Y., Zhu, H., Tang, A., Huang, D.-A., Zhu, Y., & Anandkumar, A. (2022) · arXiv · doi:10.48550/arxiv.2206.08853 · Cited by 72 · cited 2×
“…to control low-level policies [163] like a robotic transformer [101, 281, 282], which takes images and instructions as inputs and produces control commands for the end effector and robotic arms as well as virtual embodied controllers due to high costs of robotic operators [16,89,90,139,271,283,284].”
Emergent autonomous scientific research capabilities of large language models
Boiko, D. A., MacKnight, R., & Gomes, G. (2023) · arXiv · doi:10.48550/arxiv.2304.05332 · Cited by 72
CGMI: Configurable General Multi-Agent Interaction FrameworkPreprint
Jinxin, S., Zhao, J., Yilei, W., Wu, X., Li, J., & He, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.12503 · Cited by 72 · cited 1×
“Test environments may involve complex tasks for agents to cooperate on or open platforms for agents to interact freely [16,21,90,327,339,494].”
Irving, G., Christiano, P., & Amodei, D. (2018) · arXiv · doi:10.48550/arxiv.1805.00899 · Cited by 71
McCoy, R. T., Smolensky, P., Linzen, T., Gao, J., & Celikyilmaz, A. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00567 · Cited by 70 · cited 1×
“The text quality they generate excels in various aspects such as fluency, relevance, diversity, controllability [112, 225–227].”
Sebastian, G. (2023) · International Journal of Security and Privacy in Pervasive Computing · doi:10.4018/ijsppc.325475 · Cited by 70
McCoy, R. T., Smolensky, P., Linzen, T., Gao, J., & Celikyilmaz, A. (2021) · arXiv · doi:10.48550/arxiv.2111.09509 · Cited by 70 · cited 1×
“The text quality they generate excels in various aspects such as fluency, relevance, diversity, controllability [112, 225–227].”
MultiModal-GPT: a vision and language model for dialogue with humans
Gong, T., Lyu, C., Zhang, S., Wang, Y., Zheng, M., Zhao, Q., Liu, K., Zhang, W., Luo, P., & Chen, K. (2023) · arXiv · doi:10.48550/arxiv.2305.04790 · Cited by 70
Self-Polish: Enhance Reasoning in Large Language Models via Problem RefinementPreprint
Xi, Z., Jin, S.-J., Zhou, Y., Zheng, R., Gao, S., Liu, J., Gui, T., Zhang, Q., & Huang, X. (2023) · Conference on Empirical Methods in Natural Language Processing · doi:10.48550/arxiv.2305.14497 · Cited by 69 · cited 3×
“Similarly, LLMs have shown the emergent ability of planning in forms of goal reformulation [80, 108], task decomposition [79, 109], and adjusting plans in response to environmental changes [81,110].”
Self-citationTowards Revealing the Mystery behind Chain of Thought: a Theoretical Perspective
Feng, G., Zhang, B., Gu, Y., Ye, H., He, D., & Wang, L. (2023) · arXiv · doi:10.48550/arxiv.2305.15408 · Cited by 69
Language models, like humans, show content effects on reasoning tasks
Lampinen, A. K., Dasgupta, I., Chan, S. C. Y., Sheahan, H. R., Creswell, A., Kumaran, D., McClelland, J. L., & Hill, F. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae233 · Cited by 69
What might get in the way: Barriers to the use of apps for depression
Stiles-Shields, C., Montague, E., Lattie, E. G., Kwasny, M. J., & Mohr, D. C. (2017) · DIGITAL HEALTH · doi:10.1177/2055207617713827 · Cited by 68 · cited 1×
“Especially in mental health, research has shown that agents can lead to increased accessibility due to benefits such as reduced cost and anonymity compared to face-to-face treatment [372].”
Abrams, A. M. H., & der Pütten, A. M. R.-V. (2020) · International Journal of Social Robotics · doi:10.1007/s12369-020-00642-z · Cited by 68 · cited 2×
“It influences user communication experiences and significantly impacts communication efficiency, involving whether they can seamlessly interact with humans and other agents [406, 488, 489].”
Software-Based Dialogue Systems: Survey, Taxonomy, and Challenges
Motger, Q., Franch, X., & Marco, J. (2023) · ACM Computing Surveys · doi:10.1145/3527450 · Cited by 68
The alignment problem from a deep learning perspective
Ngo, R., Chan, L., & Mindermann, S. (2022) · arXiv · doi:10.48550/arxiv.2209.00626 · Cited by 68 · cited 1×
“Throughout the interaction, humans play a pivotal role by offering guidance or by regulating the safety, legality, and ethical conduct of agents [341,342].”
Hagendorff, T., Dasgupta, I., Binz, M., Chan, S. C. Y., Lampinen, A., Wang, J. X., Akata, Z., & Schulz, E. (2023) · arXiv · doi:10.48550/arxiv.2303.13988 · Cited by 68 · cited 1×
“They conducted psychology experiments about judgment and decision-making to test agent systems [413, 414, 416, 417].”
Self-citationRelational World Knowledge Representation in Contextual Language Models: A Review
Safavi, T., & Koutra, D. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.81 · Cited by 68
The Hitchhiker's Guide to Program Analysis: A Journey with Large Language ModelsPreprint
Li, H., Hao, Y., Zhai, Y., & Qian, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.00245 · Cited by 67 · cited 2×
“Experts from the computer field make full use of the agent’s powerful code comprehension and debugging abilities [288,311].”
Learning from Richer Human Guidance: Augmenting Comparison-Based Learning with Feature Queries
Basu, C., Singhal, M., & Dragan, A. D. (2018) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3171221.3171284 · Cited by 67
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction
Elgohary, A., Meek, C., Richardson, M., Fourney, A., Ramos, G., & Awadallah, A. H. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.444 · Cited by 66
Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate
Xiong, K., Ding, X., Cao, Y., Liu, T., & Qin, B. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.508 · Cited by 66
Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents
Talebirad, Y., & Nadiri, A. (2023) · arXiv · doi:10.48550/arxiv.2306.03314 · Cited by 65
Lightman, H., Kosaraju, V., Burda, Y., Edwards, H., Baker, B., Lee, T., Leike, J., Schulman, J., Sutskever, I., & Cobbe, K. (2023) · arXiv · doi:10.48550/arxiv.2305.20050 · Cited by 65 · cited 1×
“Simultaneously, techniques like process supervision can make the inference output and reasoning of LLMs more reliable [549].”
Fainstein, S. S. (2015) · Wiley eBooks · doi:10.1002/9781119084679.ch13 · Cited by 65
ChatLLM network: More brains, more intelligence
Hao, R., Hu, L., Qi, W., Wu, Q., Zhang, Y., & Nie, L. (2025) · AI Open · doi:10.1016/j.aiopen.2025.01.001 · Cited by 65
Identifying and Manipulating the Personality Traits of Language ModelsPreprint
Caron, G., & Srivastava, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.10276 · Cited by 64 · cited 1×
“Researchers analyze character traits in LLMs using frameworks like the big five personality trait measure [425, 426] and the Myers-Briggs type indicator (MBTI) [425–427].”
Inductive reasoning in humans and large language modelsPreprint
Han, S., Ransom, K., Perfors, A., & Kemp, C. (2023) · Cognitive Systems Research · doi:10.48550/arxiv.2306.06548 · Cited by 64
Grounding Open-Domain Instructions to Automate Web Support Tasks
Xu, N., Masling, S., Du, M., Campagna, G., Heck, L. P., Landay, J. A., & Lam, M. S. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.80 · Cited by 63
Inferring Rewards from Language in Context
Lin, J., Fried, D., Klein, D., & Dragan, A. D. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.585 · Cited by 63
Generative Deep Neural Networks for Dialogue: A Short Review
Serban, I. V., Lowe, R., Charlin, L., & Pineau, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.06216 · Cited by 63
Using cognitive psychology to understand GPT-3Preprint
Binz, M., & Schulz, E. (2022) · doi:10.31234/osf.io/6dfgk · Cited by 62
Chat with the Environment: Interactive Multimodal Perception Using Large Language Models
Zhao, X., Li, M., Weber, C., Hafez, M. B., & Wermter, S. (2023) · 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342363 · Cited by 62
A Review on Language Models as Knowledge Bases
AlKhamissi, B., Li, M., Celikyilmaz, A., Diab, M., & Ghazvininejad, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06031 · Cited by 62
Is GPT-3 a Psychopath? Evaluating Large Language Models from a Psychological PerspectivePreprint
Li, X., Li, Y.-T., Liu, L., Bing, L., & Joty, S. R. (2022) · arXiv.org · doi:10.48550/arxiv.2212.10529 · Cited by 61
Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study
Yao, Z., Su, Y., Sun, H., & Yih, W.-T. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1547 · Cited by 60 · cited 1×
“Furthermore, agents can learn human preference from comparative scores like multiple choice [355,356].”
Beyond Conflict Monitoring: Cognitive Control and the Neural Basis of Thinking Before You Act
Brown, J. W. (2013) · Current Directions in Psychological Science · doi:10.1177/0963721412470685 · Cited by 59 · cited 1×
“However, this is analogous to human behavioral patterns, where the principle of “think before you act” is observed [103,104].”
TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLPPreprint
Morris, J. X., Lifland, E., Yoo, J. Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.05909 · Cited by 59
Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation
Fang, T., Yang, S., Lan, K., Wong, D. F., Hu, J., Chao, L. S., & Zhang, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.01746 · Cited by 58 · cited 1×
“On the other hand, natural language generation demands the agent to produce fluent, grammatically correct, and credible content while adapting appropriate tones and emotions within contextual circumstances [112,225,493].”
ChatLLM Network: More brains, More intelligencePreprint
Hao, R., Hu, L., Qi, W., et al. (2023) · AI Open · doi:10.48550/arxiv.2304.12998 · Cited by 58 · cited 2×
“(2) Cooperation and negotiation abilities necessitate that agents effectively execute their assigned tasks in both ordered and unordered scenarios [89, 92, 323, 332].”
Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language ModelsPreprint
Li, M., Peng, B., Galley, M., Gao, J.-F., & Zhang, Z. (2023) · NAACL-HLT · doi:10.48550/arxiv.2305.14623 · Cited by 58
ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language ModelsPreprint
Chen, Z., Zhou, K., Zhang, B., et al. (2023) · Conference on Empirical Methods in Natural Language Processing · doi:10.48550/arxiv.2305.14323 · Cited by 57 · cited 1×
“LLM-based agents employ internal feedback mechanisms, often drawing insights from pre-existing models, to hone and enhance their strategies and planning approaches [138,150,174,175].”
Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning
Si, C., Zhang, Z., Qi, F., Liu, Z., Wang, Y., Liu, Q., & Sun, M. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.137 · Cited by 56 · cited 1×
“To address these issues, researchers can employ traditional techniques such as adversarial training [500, 508], adversarial data augmentation [529,530], and adversarial sample detection [531,532] to enhance the robustness of LLM-based agents.”
Wang, Z., Cai, S., Chen, G., Liu, A., Ma, X., & Liang, Y. (2023) · arXiv · doi:10.48550/arxiv.2302.01560 · Cited by 55 · cited 5×
“…to control low-level policies [163] like a robotic transformer [101, 281, 282], which takes images and instructions as inputs and produces control commands for the end effector and robotic arms as well as virtual embodied controllers due to high costs of robotic operators [16,89,90,139,271,283,284].”
InfluentialA Comprehensive Survey of Continual Learning: Theory, Method and ApplicationPreprint
Wang, L., Zhang, X., Su, H., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.00487 · Cited by 55
Beyond One-Model-Fits-All: A Survey of Domain Specialization for Large Language ModelsPreprint
Ling, C., Zhao, X.-J., Lu, J., Deng, C.-Y., Zheng, C., Wang, J., Chowdhury, T., Li, Y.-Q., Cui, H., Zhang, X.-C., et al. (2023) · arXiv.org · doi:10.48550/arxiv.2305.18703 · Cited by 54 · cited 1×
“LLM-based agents have limitations because of hallucination [228], the lack of training data and tuning for specific fields [229], untransparent decision-making process [230] and susceptibility to adversarial attacks [231].”
Self-citationBounding the Capabilities of Large Language Models in Open Text Generation with Prompt ConstraintsPreprint
Lu, A., Zhang, H., Zhang, Y., et al. (2023) · Findings · doi:10.48550/arxiv.2302.09185 · Cited by 53
Language models show human-like content effects on reasoning tasks
Dasgupta, I., Lampinen, A. K., Chan, S. C. Y., Sheahan, H. R., Creswell, A., Kumaran, D., McClelland, J. L., & Hill, F. (2022) · arXiv · doi:10.48550/arxiv.2207.07051 · Cited by 53 · cited 1×
“They conducted psychology experiments about judgment and decision-making to test agent systems [413, 414, 416, 417].”
A Theory of Universal Artificial Intelligence based on Algorithmic Complexity
Hütter, M. (2000) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0004001 · Cited by 52 · cited 1×
“This memory enables agents to use past experiences for strategy formulation and decision-making, similar to how humans do [132–134].”
Building Cooperative Embodied Agents Modularly with Large Language Models
Zhang, H., Du, W., Shan, J., Zhou, Q., Du, Y., Tenenbaum, J. B., Shu, T., & Gan, C. (2023) · arXiv · doi:10.48550/arxiv.2307.02485 · Cited by 52 · cited 4×
“Recent research on simulated societies has followed two primary lines, namely, exploring the boundaries of the collective intelligence capabilities of LLM-based agents [90, 115, 327, 330, 332] and using them to accelerate discoveries in the social sciences [16,438,439].”
InfluentialXu, J., Ung, M., Komeili, M., Arora, K., Boureau, Y.-L., & Weston, J. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.758 · Cited by 52
Instruction-Following Agents with Multimodal TransformerPreprint
Líu, H., Lee, L., Lee, K., & Abbeel, P. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.13431 · Cited by 52 · cited 1×
“A common approach entails a pre-trained vision transformer (ViT) used as the alignment module for text and visual information [101,102,267].”
Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and PlanningPreprint
Bakhtin, A., Wu, D., Lerer, A. K., Gray, J., Jacob, A. P., Farina, G., Miller, A., & Brown, N. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.05492 · Cited by 51
LLM As DBAPreprint
Zhou, X., Li, G., & Liu, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.05481 · Cited by 51
The relationship between journal productivity and obsolescence
Wallace, D. P. (1986) · Journal of the American Society for Information Science · doi:10.1002/(sici)1097-4571(198605)37:3<136::aid-asi4>3.0.co;2-r · Cited by 50
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Lin, B. Y., Fu, Y., Yang, K., Brahman, F., Huang, S., Bhagavatula, C., Ammanabrolu, P., Choi, Y., & Ren, X. (2023) · arXiv · doi:10.48550/arxiv.2305.17390 · Cited by 50 · cited 1×
“Additionally, some methods emphasize hierarchical planning [167, 168], while others underscore a strategy in which final plans are derived from reasoning steps structured in a tree-like format.”
Inductive reasoning in humans and large language models
Han, S. J., Ransom, K. J., Perfors, A., & Kemp, C. (2024) · Cognitive Systems Research · doi:10.1016/j.cogsys.2023.101155 · Cited by 50
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Lin, B. Y., Fu, Y., Yang, K., Brahman, F., Huang, S., Bhagavatula, C., Ammanabrolu, P., Choi, Y., & Ren, X. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1034 · Cited by 50
CAiRE: An Empathetic Neural ChatbotPreprint
Lin, Z., Xu, P., Winata, G. I., Siddique, F. B., Liu, Z., Shin, J., & Fung, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12108 · Cited by 50
Karpas, E., Abend, O., Belinkov, Y., Lenz, B., Lieber, O., Ratner, N., Shoham, Y., Bata, H., Levine, Y., Leyton-Brown, K., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.00445 · Cited by 49 · cited 1×
“Enhancing these agents by integrating them with planners of specific domains has shown to yield better performance [109,115,172,173].”
Towards Autonomous Testing Agents via Conversational Large Language Models
Feldt, R., Kang, S., Yoon, J., & Yoo, S. (2023) · 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase56229.2023.00148 · Cited by 49 · cited 2×
“Experts from the computer field make full use of the agent’s powerful code comprehension and debugging abilities [288,311].”
PEER: A Collaborative Language Model
Schick, T., Dwivedi-Yu, J., Jiang, Z., Petroni, F., Lewis, P., Izacard, G., You, Q., Nalmpantis, C., Grave, E., & Riedel, S. (2022) · arXiv · doi:10.48550/arxiv.2208.11663 · Cited by 49 · cited 1×
“Humans can also choose to participate in feedback at any time, guiding the agent’s learning in the right direction [366].”
Mehta, N., Teruel, M., Deng, X., Sanz, S. F., Awadallah, A. H., & Kiseleva, J. (2024) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2024.findings-eacl.87 · Cited by 49
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
Mündler, N., He, J., Jenko, S., & Vechev, M. (2023) · arXiv · doi:10.48550/arxiv.2305.15852 · Cited by 47 · cited 1×
“Additionally, language models are plagued by severe hallucination issues [544,545], making them prone to producing text that deviates from actual facts, thereby undermining the credibility of LLM-based agents.”
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
Mündler, N., He, J., Jenko, S., & Vechev, M. (2023) · arXiv (Cornell University) · doi:10.3929/ethz-b-000719979 · Cited by 47
Bellomo, N., Marsan, G. A., & Tosin, A. (2013) · SpringerBriefs in mathematics · doi:10.1007/978-1-4614-7242-1 · Cited by 46 · cited 1×
“One of the most promising and grounded research directions in modeling societies is to explore various economic and political states and their impact on social dynamics [458].”
Policy Transfer using Reward Shaping
Brys, T., Harutyunyan, A., Taylor, M. E., & Nowé, A. (2015) · doi:10.5555/2772879.2772905 · Cited by 46
Skill Reinforcement Learning and Planning for Open-World Long-Horizon TasksPreprint
Yuan, H.-Q., Zhang, C., Wang, H.-C., Xie, F.-Y., Cai, P., Dong, H., & Lu, Z.-Q. (2023) · arXiv.org · doi:10.48550/arxiv.2303.16563 · Cited by 46 · cited 3×
“Some researchers use LLM to decompose high-level task instructions into a series of sub-goals [315], basic skill sequences [314], or fundamental keyboard/mouse operations [315], gradually assisting agents in exploring the open world.”
Kenton, Z., Everitt, T., Weidinger, L., Gabriel, I., Mikulik, V., & Irving, G. (2021) · arXiv · doi:10.48550/arxiv.2103.14659 · Cited by 45
ScienceWorld: Is your Agent Smarter than a 5th Grader?
Wang, R., Jansen, P., Côté, M.-A., & Ammanabrolu, P. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.775 · Cited by 45
PandaGPT: One Model To Instruction-Follow Them All
Su, Y., Lan, T., Li, H., Xu, J., Wang, Y., & Cai, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.16355 · Cited by 45
R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
Yuan, T., He, Z., Dong, L., Wang, Y., Zhao, R., Xia, T., Xu, L., Zhou, B., Li, F., Zhang, Z., et al. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.79 · Cited by 45
Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate
Xiong, K., Ding, X., Cao, Y., Liu, T., & Qin, B. (2023) · arXiv · doi:10.48550/arxiv.2305.11595 · Cited by 45 · cited 3×
“Test environments may involve complex tasks for agents to cooperate on or open platforms for agents to interact freely [16,21,90,327,339,494].”
Modeling the impact of large language models on opinion dynamics: A simulation-based study
Li, C., Su, X., Han, H., Xue, C., Zheng, C., & Fan, C. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113353 · Cited by 45
ScienceWorld: Is your Agent Smarter than a 5th Grader?
Wang, R., Jansen, P., Côté, M.-A., & Ammanabrolu, P. (2022) · arXiv · doi:10.48550/arxiv.2203.07540 · Cited by 45 · cited 1×
“On the other hand, there is a severe lack of suitable training data in scientific domains, making it difficult for agents to comprehend the entire domain knowledge [306, 307].”
AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments
Paul, S., Roy-chowdhury, A. K., & Cherian, A. (2022) · neural information processing systems · doi:10.52202/068431-0451 · Cited by 44
Metacognition and the Use of Tools
Clarebout, G., Elen, J., Collazo, N. A. J., Lust, G., & Jiang, L. (2013) · Springer international handbooks of education · doi:10.1007/978-1-4419-5546-3_13 · Cited by 43
Human-in-the-Loop through Chain-of-ThoughtPreprint
Cai, Z., Chang, B., & Han, W. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.07932 · Cited by 43 · cited 2×
“Of course, the collaborative nature of human-agent interaction also allows humans to directly improve the agents’ output by modifying intermediate links [176, 362] or adjusting the conversation content [363].”
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
Li, Y., Wen, H., Wang, W., Li, X., Yuan, Y., Liu, G., Liu, J., Xu, W., Wang, X., Sun, Y., et al. (2024) · arXiv · doi:10.48550/arxiv.2401.05459 · Cited by 43 · cited 1×
“Considering the interactive nature of language, in this section, we assume that the dialogue between humans and agents is also interactive: the agent responds to each human instruction, refining its action through alternating iterations to ultimately meet human requirements [177,348].”
Self-citationEvaluating and Inducing Personality in Pre-trained Language ModelsPreprint
Jiang, G., Xu, M., Zhu, S., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.07550 · Cited by 43
Improving Contextual Language Models for Response Retrieval in Multi-Turn Conversation
Lu, J., Ren, X., Ren, Y., Liu, A., & Xu, Z. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401255 · Cited by 42 · cited 1×
“Although LLMs excel in language comprehension [19, 201] and multi-turn conversations [202], they inherently lack visual perception and can only understand discrete textual content.”
AlphaBlock: Embodied Finetuning for Vision-Language Reasoning in Robot ManipulationPreprint
Jin, C., Tan, W., Yang, J., Liu, B., Song, R., Wang, L., & Fu, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.18898 · Cited by 42 · cited 1×
“Besides these, AlphaBlock [272] focuses on more challenging manipulation tasks (e.g., making a smiley face using building blocks), which requires agents to have a more grounded understanding of the instructions.”
Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection
Gururangan, S., Card, D., Dreier, S., Gade, E., Wang, L., Wang, Z., Zettlemoyer, L., & Smith, N. A. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.165 · Cited by 42
Mind meets machine: Unravelling GPT-4’s cognitive psychology
Dhingra, S., Singh, M., S.B., V., Malviya, N., & Gill, S. S. (2023) · BenchCouncil Transactions on Benchmarks, Standards and Evaluations · doi:10.1016/j.tbench.2023.100139 · Cited by 42
SAPIEN: Affective Virtual Agents Powered by Large Language Models*
Hasan, M., Ozel, C., Potter, S., & Hoque, M. E. (2023) · International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) · doi:10.1109/aciiw59127.2023.10388188 · Cited by 42
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
Ghosh, D., Rahme, J., Kumar, A., Zhang, A., Adams, R. P., & Levine, S. (2021) · arXiv · doi:10.48550/arxiv.2107.06277 · Cited by 41 · cited 1×
“Traditionally, training a reinforcement learning agent requires huge sample sizes and long training time, and lacks generalization capability [52–56].”
Evaluating Psychological Safety of Large Language Models
Li, X., Li, Y., Qiu, L., Joty, S., & Bing, L. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.108 · Cited by 41
Trigg, R., Binkley, R. W., Bronaugh, R. N., & Marras, A. (1973) · The Philosophical Quarterly · doi:10.2307/2217746 · Cited by 40
Proceedings of the 5th International Technology, Education and Development Conference
Khalid, M. S. (2011) · Cited by 40
EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought
Mu, Y., Zhang, Q., Hu, M., Wang, W., Ding, M., Jin, J., Wang, B., Dai, J., Qiao, Y., & Luo, P. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.15021 · Cited by 40
Self-citationMa, Z., Mei, Y., & Su, Z. (2023) · arXiv · doi:10.48550/arxiv.2307.15810 · Cited by 40 · cited 1×
“LLMs can accurately identify user emotions, exhibit empathy [420, 421], and regulate their emotional responses [386,422,423].”
Adversarial T-shirt! Evading Person Detectors in A Physical WorldPreprint
Xu, K., Zhang, G., Liu, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11099 · Cited by 39
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Chen, W., Su, Y., Zuo, J., Yang, C., Yuan, C., Chan, C.-M., Yu, H., Lu, Y., Hung, Y.-H., Qian, C., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.10848 · Cited by 39 · cited 10×
“This includes enhancing decision-making in traditional agent frameworks, and potentially transforming domains previously dominated by human experts, like legal consultation and medical assistance [326,330].”
InfluentialSelf-citationA Recurrent Vision-and-Language BERT for Navigation
Hong, Y., Wu, Q., Qi, Y., Rodríguez-Opazo, C., & Gould, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.13922 · Cited by 38
Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration
Lyu, C., Wu, M., Wang, L., Huang, X., Liu, B., Du, Z., Shi, S., & Tu, Z. (2023) · arXiv · doi:10.48550/arxiv.2306.09093 · Cited by 38
Self-citationChoi, M., Pei, J., Kumar, S., Shu, C., & Jurgens, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.699 · Cited by 38
DERA: Enhancing large language model completions with dialog-enabled resolving agents
Nair, V., Schumacher, E., Tso, G., & Kannan, A. (2024) · Proceedings of the 6th Clinical Natural Language Processing Workshop · doi:10.18653/v1/2024.clinicalnlp-1.12 · Cited by 38
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
Manakul, P., Liusie, A., & Gales, M. J. F. (2023) · arXiv · doi:10.48550/arxiv.2303.08896 · Cited by 38
Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models
Shapira, N., Levy, M., Alavi, S. H., Zhou, X., Choi, Y., Goldberg, Y., Sap, M., & Shwartz, V. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.14763 · Cited by 37 · cited 1×
“However, understanding implied meanings within textual input remains challenging for current LLM-based agents [75, 197].”
ASSESSING THE ROLE OF SOCIAL MEDIA AND DIGITAL TECHNOLOGY IN VIOLENCE REPORTING
(17435046), T. R., & (19280797), G. M. (2018) · Contemporary Readings in Law and Social Justice · doi:10.22381/crlsj10220181 · Cited by 36
Thinking Fast and Slow in Large Language Models
Hagendorff, T., Fabi, S., & Kosiński, M. (2022) · PubMed · doi:10.48550/arxiv.2212.05206 · Cited by 36
Quantifying the Impact of Large Language Models on Collective Opinion DynamicsPreprint
Li, C., Su, X., Han, H.-Y., Xue, C., Zheng, C.-M., & Fan, C. (2023) · arXiv.org · doi:10.48550/arxiv.2308.03313 · Cited by 36 · cited 1×
“Furthermore, LLM-based agents possess persuasive abilities [397], dynamically influencing human viewpoints in various interactive scenarios [398].”
A survey of decision making in adversarial games
Li, X., Meng, M., Hong, Y., & Chen, J. (2024) · Science China Information Sciences · doi:10.1007/s11432-022-3777-y · Cited by 36 · cited 1×
“In many real-world applications, adversarial games play a pivotal role in facilitating highly efficient and effective decision-making processes [390].”
SCM: Enhancing Large Language Model with Self-Controlled Memory Framework
Wang, B., Liang, X., Yang, J., Huang, H., Wu, Z., Wu, S., Ma, Z., & Li, Z. (2026) · Lecture Notes in Computer Science · doi:10.1007/978-981-95-4158-4_12 · Cited by 36
Wong, L., Grand, G., Lew, A. K., Goodman, N. D., Mansinghka, V. K., Andreas, J., & Tenenbaum, J. B. (2023) · arXiv · doi:10.48550/arxiv.2306.12672 · Cited by 36
Importance Weighted Transfer of Samples in Reinforcement LearningPreprint
Tirinzoni, A., Sessa, A., Pirotta, M., & Restelli, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.10886 · Cited by 35
TALM: Tool Augmented Language Models
Parisi, A., Zhao, Y., & Fiedel, N. (2022) · arXiv · doi:10.48550/arxiv.2205.12255 · Cited by 35
How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
Chen, X., Ye, J., Zu, C., Xu, N., Zheng, R., Peng, M., Zhou, J., Gui, T., Zhang, Q., & Huang, X. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.00293 · Cited by 35
Self-citationBFClass: A Backdoor-free Text Classification Framework
Li, Z., Mekala, D., Dong, C., & Shang, J. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.40 · Cited by 34
Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents
Huang, Z., Gutierrez, S., Kamana, H., & Macneil, S. (2023) · Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586182.3615796 · Cited by 34 · cited 2×
“Some work introduces the concept of interactive memory objects, representing dialogue history that can be moved, edited, deleted, or combined through summarization [142].”
Decision-Oriented Dialogue for Human-AI Collaboration
Lin, J., Tomlin, N., Andreas, J., & Eisner, J. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00679 · Cited by 34 · cited 2×
“These foundational capabilities include environmental comprehension, reasoning, planning, decision-making, tool utilization, and embodied action capabilities, and researchers can conduct a more detailed assessment of these spe-cific capabilities [75, 396, 486, 487].”
Continual Learning of Natural Language Processing Tasks: A Survey
Ke, Z., & Liu, B. (2022) · arXiv · doi:10.48550/arxiv.2211.12701 · Cited by 34
Playing Text-Based Games with Common SensePreprint
Dambekodi, S. N., Frazier, S., Ammanabrolu, P., & Riedl, M. O. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.02757 · Cited by 33
Yoo, K., Kim, J., Jang, J., & Kwak, N. (2022) · Findings of the Association for Computational Linguistics: ACL 2022 · doi:10.18653/v1/2022.findings-acl.289 · Cited by 33
Tandon, N., Madaan, A., Clark, P., & Yang, Y. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.26 · Cited by 33 · cited 1×
“Additionally, agents can utilize a memory module to store feedback for future reuse [359].”
Distilling Internet-Scale Vision-Language Models into Embodied AgentsPreprint
Sumers, T. R., Marino, K., Ahuja, A., Fergus, R., & Dasgupta, I. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.12507 · Cited by 33 · cited 1×
“Sumers et al. [287] endeavored to amalgamate text distillation with hindsight experience replay to construct a dataset for training.”
Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
Fu, Y., Peng, H. M., Khot, T., & Lapata, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.10142 · Cited by 33 · cited 4×
“Researchers first delve into the fundamental debating abilities of LLM-based agents [114, 339, 340].”
InfluentialZhu, X., Chen, Y., Tian, H., Tao, C., Su, W., Yang, C., Huang, G., Li, B., Lu, L., Wang, X., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.17144 · Cited by 33 · cited 2×
“…to control low-level policies [163] like a robotic transformer [101, 281, 282], which takes images and instructions as inputs and produces control commands for the end effector and robotic arms as well as virtual embodied controllers due to high costs of robotic operators [16,89,90,139,271,283,284].”
Self-citationExploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt EngineeringPreprint
Junprung, E. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.07411 · Cited by 33 · cited 1×
“Taking werewolf game [404,455] and murder mystery games [456] as examples, researchers explore the capabilities of LLM-based agents when confronted with challenges of deceit, trust, and incomplete information.”
Augmenting Autotelic Agents with Large Language ModelsPreprint
Colas, C., Teodorescu, L., Oudeyer, P., Yuan, X., & Côté, M.-A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.12487 · Cited by 32
Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf
Xu, Y., Wang, S., Li, P., Luo, F., Wang, X., Liu, W., & Liu, Y. (2023) · arXiv · doi:10.48550/arxiv.2309.04658 · Cited by 32 · cited 3×
“Recently, LLM-based agents have exhibited spontaneous social behaviors in an environment [404].”
Self-citationLearning Rewards From Linguistic Feedback
Sumers, T. R., Ho, M. K., Hawkins, R. D., Narasimhan, K., & Griffiths, T. L. (2021) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v35i7.16749 · Cited by 32
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
Lai, Y., Li, C., Wang, Y., Zhang, T., Zhong, R., Zettlemoyer, L., Yih, S., Fried, D., Wang, S., & Yu, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.11501 · Cited by 31 · cited 1×
“Professional domain knowledge refers to the knowledge associated with a specific domain like programming [124, 126, 127], mathematics [128], medicine [129], etc.”
WebArena: A Realistic Web Environment for Building Autonomous Agents
Zhou, S., Xu, F. F., Zhu, H., Zhou, X., Lo, R., Sridhar, A., Cheng, X., Ou, T., Bisk, Y., Fried, D., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.13854 · Cited by 31 · cited 5×
“…virtual simulation environments and the real physical world: Virtual environments are scenes-constrained, task-specific, and interacted with in a simulated manner [292,563], while real-world environments are boundless, accommodate a wide range of tasks, and interact with in a physical manner.”
InfluentialWang, L., Fu, F., & Chen, X. (2024) · Science China Information Sciences · doi:10.1007/s11432-024-3997-0 · Cited by 31
Chain of Hindsight Aligns Language Models with Feedback
Liu, H., Sferrazza, C., & Abbeel, P. (2023) · arXiv · doi:10.48550/arxiv.2302.02676 · Cited by 30 · cited 1×
“Similarly, LLMs have shown the emergent ability of planning in forms of goal reformulation [80, 108], task decomposition [79, 109], and adjusting plans in response to environmental changes [81,110].”
Unlimiformer: Long-Range Transformers with Unlimited Length Input
Bertsch, A., Alon, U., Neubig, G., & Gormley, M. R. (2023) · arXiv · doi:10.48550/arxiv.2305.01625 · Cited by 30 · cited 1×
“When dealing with an infinite and open world, the agent’s limited context also poses significant challenges [565,566].”
ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
Chen, Z., Zhou, K., Zhang, B., Gong, Z., Zhao, X., & Wen, J.-R. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.985 · Cited by 30
Pre-trained Language Models as Prior Knowledge for Playing Text-based Games
Singh, I., Singh, G., & Modi, A. (2022) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/gbmr8139 · Cited by 30
A psychometric framework for evaluating and shaping personality traits in large language models
Serapio-García, G., Safdari, M., Crepy, C., Sun, L., Fitz, S., Romero, P., Abdulhai, M., Faust, A., & Matarić, M. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01115-6 · Cited by 30
SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning
Rana, K., Haviland, J., Garg, S., Abou-Chakra, J., Reid, I., & Suenderhauf, N. (2023) · arXiv · doi:10.48550/arxiv.2307.06135 · Cited by 29 · cited 1×
“Furthermore, they could gather feedback from tangible or virtual surroundings, such as cues from task accomplishments or post-action observations, aiding them in revising and refining their plans [72,82,178–180].”
RL4F: Generating natural language feedback with reinforcement learning for repairing model outputs
Akyurek, A. F., Akyurek, E., Kalyan, A., Clark, P., Wijaya, D. T., & Tandon, N. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.427 · Cited by 29
Advances in Multi-turn Dialogue Comprehension: A SurveyPreprint
Zhang, Z., & Zhao, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.04984 · Cited by 29
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social GoodPreprint
Wang, X., Shi, W., Kim, R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.06725 · Cited by 28 · cited 1×
“Furthermore, LLM-based agents possess persuasive abilities [397], dynamically influencing human viewpoints in various interactive scenarios [398].”
Self-citationWong, A. K. C., Wang, X. Y., & Hryniowski, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.05835 · Cited by 28
Self-citationPromptAttack: Prompt-Based Attack for Language Models via Gradient Search
Shi, Y., Li, P., Yin, C., Han, Z., Zhou, L., & Liu, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17120-8_53 · Cited by 28
Think Before You Act: Decision Transformers with Working MemoryPreprint
Kang, J., Laroche, R., Yuan, X., Trischler, A., Liu, X., & Fu, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.16338 · Cited by 28 · cited 1×
“However, this is analogous to human behavioral patterns, where the principle of “think before you act” is observed [103,104].”
Self-citationVarshney, N., Yao, W., Zhang, H., Chen, J., & Yu, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.03987 · Cited by 28
You Only Look at Screens: Multimodal Chain-of-Action Agents
Zhang, Z., & Zhang, A. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.186 · Cited by 28
Towards Healthy AI: Large Language Models Need Therapists Too
Lin, B., Bouneffouf, D., Cecchi, G., & Varshney, K. (2024) · Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024) · doi:10.18653/v1/2024.trustnlp-1.6 · Cited by 28
Large language models as tool makers
Cai, T., Wang, X., Ma, T., Chen, X., & Zhou, D. (2023) · arXiv · doi:10.48550/arxiv.2305.17126 · Cited by 28
Self-citationChatGPT as your Personal Data ScientistPreprint
Hassan, M. M., Knipper, R. A., & Karmaker, S. (. (2023) · arXiv.org · doi:10.48550/arxiv.2305.13657 · Cited by 27
“Personhood and AI: Why large language models don’t understand us”
Browning, J. (2024) · AI & SOCIETY · doi:10.1007/s00146-023-01724-y · Cited by 27
OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMs
Haller, P., Aynetdinov, A., & Akbik, A. (2024) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2024.naacl-demo.8 · Cited by 27
Ogundare, O., Madasu, S., & Wiggins, N. (2023) · International Conference on Control, Mechatronics and Automation (ICCMA) · doi:10.1109/iccma59762.2023.10374622 · Cited by 27 · cited 1×
“Tools for non-textual output can diversify the modalities of agent actions, thereby expanding the application scenarios of LLM-based agents [163,247].”
Limitations of Autoregressive Models and Their Alternatives
Lin, C.-C., Jaech, A., Li, X., Gormley, M. R., & Eisner, J. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.405 · Cited by 27
Estimating the Personality of White-Box Language Models
Karra, S. R., Nguyen, S. T., & Tulabandhula, T. (2022) · arXiv · doi:10.48550/arxiv.2204.12000 · Cited by 27 · cited 1×
“Researchers analyze character traits in LLMs using frameworks like the big five personality trait measure [425, 426] and the Myers-Briggs type indicator (MBTI) [425–427].”
Generating Executable Action Plans with Environmentally-Aware Language Models
Gramopadhye, M., & Szafir, D. (2023) · 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341989 · Cited by 26
An intelligent system for document retrieval in distributed office environments
Mukhopadhyay, U., Stephens, L. M., Huhns, M. N., & Bonnell, R. D. (1986) · Journal of the American Society for Information Science · doi:10.1002/asi.4630370304 · Cited by 26
Kirk, H. R., Jun, Y., Iqbal, H., Benussi, E., Volpin, F., Dreyer, F. A., Shtedritski, A., & Asano, Y. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.04130 · Cited by 25 · cited 1×
“A large part of the reason lies in the training corpora obtained from the Internet [463,464], which reflect, and sometimes even amplify real-world social biases such as gender, religion, and culture [465].”
Playing the Werewolf game with artificial intelligence for language understandingPreprint
Shibata, H., Miki, S., & Nakamura, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.10646 · Cited by 25 · cited 1×
“Taking werewolf game [404,455] and murder mystery games [456] as examples, researchers explore the capabilities of LLM-based agents when confronted with challenges of deceit, trust, and incomplete information.”
Charan, P. V. S., Chunduri, H., Anand, P. M., & Shukla, S. K. (2023) · arXiv · doi:10.48550/arxiv.2305.15336 · Cited by 25
Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA
Smith, J. S., Hsu, Y.-C., Zhang, L., Hua, T., Kira, Z., Shen, Y., & Jin, H. (2023) · arXiv · doi:10.48550/arxiv.2304.06027 · Cited by 25
Agent oriented programming: An overview of the framework and summary of recent research
Shoham, Y. (1994) · Lecture notes in computer science · doi:10.1007/3-540-58095-6_9 · Cited by 24
Interactive Fiction Games: A Colossal AdventurePreprint
Hausknecht, M., Ammanabrolu, P., Côté, M.-A., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05398 · Cited by 24
Mindstorms in Natural Language-Based Societies of Mind
Zhuge, M., Liu, H., Faccio, F., Ashley, D. R., Csordás, R., Gopalakrishnan, A., Hamdi, A., Hammoud, H. A. A. K., Herrmann, V., Irie, K., et al. (2025) · Computational Visual Media · doi:10.26599/cvm.2025.9450460 · Cited by 24 · cited 1×
“However, current research predominantly involves a limited number of agents, and very few efforts have been made to scale up the number of agents to create more complex systems or simulate larger societies [561, 562].”
Self-citationMindstorms in Natural Language-Based Societies of Mind
Zhuge, M., Liu, H., Faccio, F., Ashley, D. R., Csordás, R., Gopalakrishnan, A., Hamdi, A., Hammoud, H. A. A. K., Herrmann, V., Irie, K., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.17066 · Cited by 24 · cited 1×
“However, current research predominantly involves a limited number of agents, and very few efforts have been made to scale up the number of agents to create more complex systems or simulate larger societies [561, 562].”
Self-citationOpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMsPreprint
Haller, P., Aynetdinov, A., & Akbik, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.03876 · Cited by 24
CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models
Qian, C., Han, C., Fung, Y., Qin, Y., Liu, Z., & Ji, H. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.462 · Cited by 24
Faithful Chain-of-Thought Reasoning
Lyu, Q., Havaldar, S., Stein, A., Zhang, L., Rao, D., Wong, E., Apidianaki, M., & Callison-Burch, C. (2023) · arXiv · doi:10.48550/arxiv.2301.13379 · Cited by 23 · cited 1×
“In contrast, other studies like the CoT-series employ an adaptive strategy, where they plan and address sub-tasks one at a time, allowing for more fluidity in handling intricate tasks in their entirety [76, 77, 166].”
Aziz, H. (2010) · ACM SIGACT News · doi:10.1145/1753171.1753181 · Cited by 22 · cited 1×
“However, researchers increasingly recognize that introducing concepts from game theory [333, 334] into systems can lead to more robust and efficient behaviors.”
Shortcut Learning of Large Language Models in Natural Language UnderstandingPreprint
Du, M., He, F., Zou, N., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.11857 · Cited by 22 · cited 1×
“Furthermore, employing debiasing methods and calibration techniques can also mitigate the potential fairness issues within LLMs [551,552].”
A Close Look into the Calibration of Pre-trained Language Models
Chen, Y., Yuan, L., Cui, G., Liu, Z., & Ji, H. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.75 · Cited by 22
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
Bach, S. H., Sanh, V., Yong, Z.-X., Webson, A., Raffel, C., Nayak, N. V., Sharma, A., Kim, T., Bari, M. S., Fevry, T., et al. (2022) · arXiv · doi:10.48550/arxiv.2202.01279 · Cited by 21 · cited 1×
“With just task descriptions or demonstrations, they can effectively handle previously unseen tasks [18, 87, 478].”
GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-SpeechPreprint
Huang, R., Ren, Y., Liu, J., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.07211 · Cited by 21
Helping the Helper: Supporting Peer Counselors via AI-Empowered Practice and FeedbackPreprint
Hsu, S.-L., Shah, R. S., Senthil, P., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.08982 · Cited by 21 · cited 2×
“Hsu et al. [374] built contextualized language generation approaches to provide tailored assistance for users who seek support on diverse topics ranging from relationship stress to anxiety.”
Emergent Analogical Reasoning in Large Language ModelsPreprint
Webb, T. W., Holyoak, K. J., & Lu, H. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.09196 · Cited by 21
Kwon, D., Lee, S., Kim, K. H., Lee, S., Kim, T.-Y., & Davis, E. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-industry.68 · Cited by 21
Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation
Ren, R., Wang, Y., Qu, Y., Zhao, W. X., Liu, J., Tian, H., Wu, H., Wen, J.-R., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2307.11019 · Cited by 21
Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity
Shuster, K., Urbanek, J., Szlam, A., & Weston, J. (2022) · Findings of the Association for Computational Linguistics: NAACL 2022 · doi:10.18653/v1/2022.findings-naacl.182 · Cited by 20
(2018) · Routledge eBooks · doi:10.4324/9781351165129 · Cited by 19
LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language ModelsPreprint
Song, C. H., Wu, J., Washington, C. B., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.04088 · Cited by 19
Epidemic Modeling with Generative Agents
Williams, R., Hosseinichimeh, N., Majumdar, A., & Ghaffarzadegan, N. (2023) · arXiv · doi:10.48550/arxiv.2307.04986 · Cited by 19
Tandon, N., Madaan, A., Clark, P., & Yang, Y. (2021) · arXiv · doi:10.48550/arxiv.2112.09737 · Cited by 19 · cited 1×
“Additionally, agents can utilize a memory module to store feedback for future reuse [359].”
CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement LearningPreprint
Jhan, J.-H., Liu, C.-P., Jeng, S., & Lee, H.-Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.03949 · Cited by 18 · cited 1×
“Natural language understanding requires the agent to not only comprehend literal meanings but also grasp implied meanings and relevant social knowledge and rhetoric, such as humor, irony, aggression, and emotions [490–492].”
A Close Look into the Calibration of Pre-trained Language Models
Chen, Y., Yuan, L., Cui, G., Liu, Z., & Ji, H. (2022) · arXiv · doi:10.48550/arxiv.2211.00151 · Cited by 18 · cited 1×
“Similar to other neural networks, LLMs struggle to express the certainty of their predictions precisely [537, 539].”
SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
Miao, N., Teh, Y. W., & Rainforth, T. (2023) · arXiv · doi:10.48550/arxiv.2308.00436 · Cited by 18
Training Socially Aligned Language Models on Simulated Social Interactions
Liu, R., Yang, R., Jia, C., Zhang, G., Zhou, D., Dai, A. M., Yang, D., & Vosoughi, S. (2023) · arXiv · doi:10.48550/arxiv.2305.16960 · Cited by 18 · cited 8×
“Moreover, the capabilities of LLM-based agents must be constrained to a safe scope of application to prevent unintended harm to other elements in the environment, placing higher demands on LLMs serving as the cognitive core [21, 479,480].”
InfluentialScaling Imitation Learning in MinecraftPreprint
Amiranashvili, A., Dorka, N., Burgard, W., Koltun, V., & Brox, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02701 · Cited by 17 · cited 1×
“Early efforts mainly focused on reinforcement learning [177, 312] and imitation learning [313], enabling agents to craft some low-level items.”
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Xu, B., Peng, Z., Lei, B., Mukherjee, S., Liu, Y., & Xu, D. (2023) · arXiv · doi:10.48550/arxiv.2305.18323 · Cited by 17
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Gur, I., Furuta, H., Huang, A., Safdari, M., Matsuo, Y., Eck, D., & Faust, A. (2023) · arXiv · doi:10.48550/arxiv.2307.12856 · Cited by 17 · cited 3×
“In task-oriented deployment, the agent follows high-level instructions from users, undertaking tasks such as goal decomposition [167,171,293,294], sequence planning of sub-goals [167,295], interactive exploration of the environment [165,292,296,297], until the final objective is achieved.”
Huang, X., Ruan, W., Huang, W., et al. (2023) · Research Explorer (The University of Manchester) · doi:10.48550/arxiv.2305.11391 · Cited by 16 · cited 2×
“Ensuring trustworthiness has consistently remained a critically important yet challenging issue within the field of deep learning [535–537].”
Self-citation
Research works printed but not linked: 44
- Russell S. Artificial Intelligence: A Modern Approach. Upper Saddle River: Pearson Education, Inc., 2020
- Schlosser M. Agency. In: The Stanford Encyclopedia of Philosophy. Stanford: The Metaphysics Research Lab, 2019
- Hutter M. Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Berlin: Springer, 2004
- Anscombe G E M. Intention. Cambridge: Harvard University Press, 2000
- Nilsson N J. Toward Agent Programs With Circuit Semantics. Technical Report, No. STAN-CS-92-1412, 1992
- Shardlow N. Action and agency in cognitive science. Dissertation for Master’s Degree. Oxford: University of Manchester, 1990
- Sacerdoti E D. The nonlinear nature of plans. In: Proceedings of Advance Papers of the Fourth International Joint Conference on Artificial Intelligence, Tbilisi, 1975. 206–214
- Taylor M E, Stone P. Transfer learning for reinforcement learning domains: a survey. J Mach Learn Res, 2009, 10: 1633–1685
- Liu H, Sferrazza C, Abbeel P. Languages are rewards: hindsight finetuning using human feedback. 2023. ArXiv:2302.02676 · arXiv
- Darwin C. On the Origin of Species: Facsimile of the First Edition. London: John Murray, 1859. 24: 1
- Nuxoll A M, Laird J E. Extending cognitive architecture with episodic memory. In: Proceedings of AAAI, 2007. 1560–1564
- Shinn N, Labash B, Gopinath A. Reflexion: an autonomous agent with dynamic memory and self-reflection. 2023. ArXiv:2303.11366 · arXiv
- Sebastia L, Onaindia E, Marzal E. Decomposition of planning problems. AI Commun, 2006, 19: 49–81
- Solaiman I, Dennison C. Process for adapting language models to society (PALMS) with values-targeted datasets. In: Proceedings of Advances in Neural Information Processing Systems, 2021. 34: 5861–5873
- Gong Y, Chung Y, Glass J R. AST: audio spectrogram transformer. In: Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Brno, 2021. 571–575
- Almazrouei E, Alobeidli H, Alshamsi A, et al. Falcon-40B: an open large language model with state-of-the-art performance. 2023. https://falconllm.tii.ae
- Radford A, Wu J, Child R, et al. Language models are unsupervised multitask learners. OpenAI blog, 2019, 1: 9
- Nguyen H, La H M. Review of deep reinforcement learning for robot manipulation. In: Proceedings of the 3rd IEEE International Conference on Robotic Computing, Naples, 2019. 590–595
- Finin T W, Fritzson R, McKay D P, et al. KQML as an agent communication language. In: Proceedings of the 3rd International Conference on Information and Knowledge Management (CIKM’94), Gaithersburg, 1994. 456–463
- Weston J. Dialog-based language learning. In: Proceedings of Advances in Neural Information Processing Systems, 2016. 829–837
- Kreutzer J, Khadivi S, Matusov E, et al. Can neural machine translation be improved with user feedback? In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018. 92–105
- Mehta N, Goldwasser D. Improving natural language interaction with robots using advice. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, 2019. 1962–1967
- Hancock B, Bordes A, Mazare P, et al. Learning from dialogue after deployment: feed yourself, chatbot! In: Proceedings of the 57th Conference of the Association for Computational Linguistics, 2019. 3667–3684
- Gvirsman O, Koren Y, Norman T, et al. Patricc: a platform for triadic interaction with changeable characters. In: Proceedings of ACM/IEEE International Conference on Human-Robot Interaction, Cambridge, 2020. 399–407
- Gao W, Gao X, Tang Y. Multi-turn dialogue agent as sales’ assistant in telemarketing. In: Proceedings of International Joint Conference on Neural Networks, Gold Coast, 2023. 1–9
- Adamopoulou E, Moussiades L. Chatbots: history, technology, and applications. Machine Learn Appl, 2020, 2: 100006
- Zhou X, Wang W Y. MojiTalk: generating emotional responses at scale. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, 2018. 1128–1137
- Sabour S, Zheng C, Huang M. CEM: commonsense-aware empathetic response generation. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence, the 34th Conference on Innovative Applications of Artificial Intelligence, the 12th Symposium on Educational Advances in Artificial Intelligence, 2022. 11229–11237
- Curry A, Curry A C. Computer says “no”: the case against empathetic conversational AI. In: Proceedings of Findings of the Association for Computational Linguistics, Toronto, 2023. 8123–8130
- Hollan J D, Hutchins E L, Weitzman L. STEAMER: an interactive inspectable simulation-based training system. AI Mag, 1984, 5: 15–27
- Tambe M, Johnson W L, Jones R M, et al. Intelligent agents for interactive simulation environments. AI Mag, 1995, 16: 15–39
- Hendrickx J M, Martin S. Open multi-agent systems: gossiping with random arrivals and departures. In: Proceedings of the 56th IEEE Annual Conference on Decision and Control, Melbourne, 2017. 763–768
- Aher G V, Arriaga R I, Kalai A T. Using large language models to simulate multiple humans and replicate human subject studies. In: Proceedings of International Conference on Machine Learning, Honolulu, 2023. 337–371
- Goodfellow I J, Shlens J, Szegedy C. Explaining and harnessing adversarial examples. In: Proceedings of the 3rd International Conference on Learning Representations, San Diego, 2015
- Hendrycks D, Dietterich T G. Benchmarking neural network robustness to common corruptions and perturbations. In: Proceedings of the 7th International Conference on Learning Representations, 2019
- Rigter M, Lacerda B, Hawes N. RAMBO-RL: robust adversarial model-based offline reinforcement learning. In: Proceedings of Conference on Neural Information Processing Systems, 2022
- Lab T K S. Experimental security research of Tesla autopilot. Tencent Keen Security Lab, 2019. https://keenlab.tencent.com/en/whitepapers/Experimental_Security_Research_of_Tesla_Autopilot.pdf
- Sharif M, Bhagavatula S, Bauer L, et al. Accessorize to a crime: real and stealthy attacks on state-of-the-art face recognition. In: Proceedings of the ACM SIGSAC Conference on Computer and Communications Security, Vienna, 2016. 1528–1540
- Carlini N, Wagner D A. Audio adversarial examples: targeted attacks on speech-to-text. In: Proceedings of IEEE Security and Privacy Workshops, San Francisco, 2018. 1–7
- Guo Y, Yang Y, Abbasi A. Auto-Debias: debiasing masked language models with automated biased prompts. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Dublin, 2022. 1012–1023
- Elhage N, Nanda N, Olsson C, et al. A mathematical framework for transformer circuits. Transformer Circ Thread, 2021, 1: 12
- Chowdhury J R, Caragea C. Monotonic location attention for length generalization. In: Proceedings of International Conference on Machine Learning, Honolulu, 2023. 28792–28808
- Bhardwaj S, Jain L, Jain S. Cloud computing: a study of infrastructure as a service (IAAS). Int J Engin Inform Technol, 2010, 2: 60–63
- Dubey A, Wagle D. Delivering software as a service. The McKinsey Quart, 2007, 6: 2007
Cited by
A Comprehensive Overview of Large Language Models
Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., & Mian, A. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3744746 · Cited by 1,257
Unleashing the potential of prompt engineering for large language models
Chen, B., Zhang, Z., Langrené, N., & Zhu, S. (2025) · Patterns · doi:10.1016/j.patter.2025.101260 · Cited by 490
Demystifying LLM-Based Software Engineering Agents
Xia, C. S., Deng, Y., Dunn, S., & Zhang, L. (2025) · Proceedings of the ACM on Software Engineering · doi:10.1145/3715754 · Cited by 849
AI Alignment: A Contemporary Survey
Ji, J., Qiu, T., Chen, B., Zhou, J., Zhang, B., Hong, D., Lou, H., Wang, K., Duan, Y., He, Z., et al. (2025) · ACM Computing Surveys · doi:10.1145/3770749 · Cited by 809
Multi-Agent Collaboration Mechanisms: A Survey of LLMs
Tran, K.-T., Dao, D., Nguyen, M.-D., Pham, Q.-V., O'Sullivan, B., & Nguyen, H. D. (2025) · arXiv · doi:10.48550/arxiv.2501.06322 · Cited by 680
Metadata
- Authors
- Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., Zheng, R., Fan, X., Wang, X., Xiong, L., Zhou, Y., Wang, W., Jiang, C., Zou, Y., Liu, X., Yin, Z., Dou, S., Weng, R., Qin, W., Zheng, Y., Qiu, X., Huang, X., Zhang, Q., & Gui, T.
- Affiliations
- Fudan University (CN)
- Meituan (China) (CN)
- Corresponding author
- Zhang, Qi
- Gui, Tao
- ORCID
- Venue
- Science China Information Sciences
- Published
- 2025-01-17
- Volume
- 68
- Issue
- 2
- ISSN
- 1869-1919 (ISSN-L)
- 1674-733X
- OpenAlex
- W4406800520
- Semantic Scholar
- 7fa2d1632262f30921aa0415f1b4c0f15f50e865
- Cited by
- 970
- References
- 485
- Citations by year
- 2026: 462 · 2025: 338
- FWCI
- 320.88
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- other-oa
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- Science China Information Sciences (publishedVersion)
- arXiv (Cornell University) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Keywords
- large language models, LLM agents, AI agents, artificial general intelligence, agent applications
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.