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 601–704 of 704
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
Xi, Z., Jin, S., Zhou, Y., Zheng, R., Gao, S., Liu, J., Gui, T., Zhang, Q., & Huang, X. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.762 · Cited by 16
Self-citationCAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model SocietyPreprint
Li, G., Hammoud, H. A. A. K., Itani, H., Khizbullin, D., & Ghanem, B. (2023) · King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology) · Cited by 16
Social Simulacra: Creating Populated Prototypes for Social Computing SystemsPreprint
Park, J.-S., Popowski, L., Cai, C. J., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.04024 · Cited by 15 · cited 1×
“Techniques like prompt engineering [16,430] and personality-enriched datasets [431,432] are used to optimize LLMs and train them to exhibit specific personality traits.”
Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
Hu, B., Zhao, C., Zhang, P., Zhou, Z., Yang, Y., Xu, Z., & Liu, B. (2023) · arXiv · doi:10.48550/arxiv.2306.03604 · Cited by 15 · cited 1×
“Some studies [72,81,82,266] dynamically generated, maintained, and adjusted high-level action plans in order to minimize dependency on prior knowledge, thereby grounding the plan.”
Hagendorff, T., & Fabi, S. (2023) · arXiv · doi:10.48550/arxiv.2306.07622 · Cited by 15 · cited 1×
“Specifically, LLMs have been evaluated using the cognitive reflection test (CRT) to underscore their capacity for deliberate thinking beyond mere intuition [418, 419].”
MEGA: Multilingual Evaluation of Generative AI
Ahuja, K., Diddee, H., Hada, R., Ochieng, M., Ramesh, K., Jain, P., Nambi, A., Ganu, T., Segal, S., Axmed, M., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12528 · Cited by 15
Reference Resolution Challenges for Intelligent Agents: The Need for Knowledge
McShane, M. J. (2009) · IEEE Intelligent Systems · doi:10.1109/mis.2009.79 · Cited by 14 · cited 1×
“Furthermore, the knowledge can assist LLM-based agents in making informed decisions [121].”
Analyzing Description, User Understanding and Expectations of AI in Mobile Health Applications
Su, Z., Figueiredo, M. C., Jo, J., Zheng, K., & Chen, Y. (2020) · PubMed Central · doi:10.13140/rg.2.2.10530.25280 · Cited by 14
Collaborating with language models for embodied reasoning
Dasgupta, I., Kaeser-Chen, C., Marino, K., Ahuja, A., Babayan, S., Hill, F., & Fergus, R. (2023) · arXiv · doi:10.48550/arxiv.2302.00763 · Cited by 14 · cited 1×
“Recent studies have indicated that leveraging the rich internal knowledge acquired during the pre-training of LLMs can effectively alleviate these issues [101,171,178,253].”
Training Language Models with Language Feedback at Scale
Scheurer, J., Campos, J. A., Korbak, T., Chan, J. S., Chen, A., Cho, K., & Perez, E. (2023) · arXiv · doi:10.48550/arxiv.2303.16755 · Cited by 14
AgentSims: An Open-Source Sandbox for Large Language Model Evaluation
Lin, J., Zhao, H., Zhang, A., Wu, Y., Ping, H., & Chen, Q. (2023) · arXiv · doi:10.48550/arxiv.2308.04026 · Cited by 14 · cited 4×
“With the development of LLM-based agents, micro-level simulation has gained prominence recently [16, 140].”
InfluentialBlind Judgement: Agent-Based Supreme Court Modelling With GPT
Hamilton, S. (2023) · arXiv · doi:10.48550/arxiv.2301.05327 · Cited by 13
Phelps, S., & Russell, Y. I. (2023) · Middlesex University Research Repository (Middlesex University Of London) · doi:10.48550/arxiv.2305.07970 · Cited by 13
ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
Hu, C., Fu, J., Du, C., Luo, S., Zhao, J., & Zhao, H. (2023) · arXiv · doi:10.48550/arxiv.2306.03901 · Cited by 13 · cited 3×
“Similarly, other studies allow for memory operations like deletion based on specific commands provided by users [143].”
InfluentialEfficient Adversarial Training with Robust Early-Bird Tickets
Xi, Z., Zheng, R., Gui, T., Zhang, Q., & Huang, X. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.569 · Cited by 13
Self-citationVisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image CaptioningPreprint
Chen, J., Guo, H., Yi, K., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.10407 · Cited by 13
Probing Pre-trained Language Models for Semantic Attributes and their Values
Beloucif, M., & Biemann, C. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.218 · Cited by 13
Hierarchical principles of embodied reinforcement learning: A reviewPreprint
Eppe, M., Gumbsch, C., Kerzel, M., Nguyen, P. D. H., Butz, M. V., & Wermter, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.10147 · Cited by 12
Nottingham, K., Ammanabrolu, P., Suhr, A., Choi, Y., Hajishirzi, H., Singh, S., & Fox, R. (2023) · arXiv · doi:10.48550/arxiv.2301.12050 · Cited by 12 · cited 2×
“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.”
‘Dynamics of Growth in a Finite World’ – Comprehensive Sensitivity Analysis
Vermeulen, P. J., & de Jongh, D. C. J. (1976) · IFAC Proceedings Volumes · doi:10.1016/s1474-6670(17)67333-6 · Cited by 11 · cited 1×
“In the macro-level simulation, also known as system-based simulation, researchers model the overall state of the system of the simulated society [444, 445].”
Chen, J., Guo, H., Yi, K., Li, B., & Elhoseiny, M. (2021) · arXiv (Cornell University) · Cited by 11
NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language ModelsPreprint
Zhou, G., Hong, Y., & Wu, Q. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.16986 · Cited by 11 · cited 1×
“A memory mechanism is needed to record historical information [277], which is also adopted in Smallville and Voyager [16, 177,278, 279].”
Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?Preprint
Lu, B.-R., Haduong, N., Lee, C., Wu, Z., Cheng, H., Koester, P., Utke, J., Yu, T., Smith, N. A., & Ostendorf, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.07047 · Cited by 11
Wang, Z., Mao, S., Wu, W., Ge, T., Wei, F., & Ji, H. (2023) · arXiv · doi:10.48550/arxiv.2307.05300 · Cited by 11 · cited 2×
“Research has shown that within this simulated society, experts with different backgrounds and abilities contribute to creative solutions to complex problems (e.g., software development or consulting) [89, 90, 324, 330].”
TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage
Ruan, J., Chen, Y., Zhang, B., Xu, Z., Bao, T., Du, G., Shi, S., Mao, H., Li, Z., Zeng, X., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.03427 · Cited by 11 · cited 2×
“Coupled with the knowledge and memory they acquired, LLMs can create coherent action sequences that can be executed effectively [171,246,271].”
Quantifying the Impact of Large Language Models on Collective Opinion DynamicsPreprint
Li, C., Su, X., Han, H., Xue, C., Zheng, C., & Fan, C. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4688547 · Cited by 11
Look, Listen, and Act: Towards Audio-Visual Embodied NavigationPreprint
Gan, C., Zhang, Y., Wu, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.11684 · Cited by 10 · cited 1×
“Previous studies demonstrate a basic framework that includes a dynamic path planner that uses visual and auditory observations along with spatial memories to plan a series of actions [265,280].”
Learning to Solve Voxel Building Embodied Tasks from Pixels and Natural Language InstructionsPreprint
Skrynnik, A., Volovikova, Z., Côté, M.-A., Voronov, A. Y., Zholus, A., Arabzadeh, N., Mohanty, S., Teruel, M., Awadallah, A. H., Panov, A. I., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.00688 · Cited by 10 · cited 1×
“Early efforts mainly focused on reinforcement learning [177, 312] and imitation learning [313], enabling agents to craft some low-level items.”
Images Speak in Images: A Generalist Painter for In-Context Visual LearningPreprint
Wang, X., Wang, W., Cao, Y., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.02499 · Cited by 10 · cited 1×
“Beyond texts, researchers also explore the potential ICL capabilities in different multimodal tasks [189–194], making it possible for agents to be applied to large-scale real-world tasks.”
Self-citationEmpathetic AI for Empowering Resilience in GamesPreprint
Habibi, R., Pfau, J., Holmes, J., & El‐Nasr, M. S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.09070 · Cited by 10 · cited 1×
“LLMs can accurately identify user emotions, exhibit empathy [420, 421], and regulate their emotional responses [386,422,423].”
S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents
Gao, C., Lan, X., Lu, Z., Mao, J., Piao, J., Wang, H., Jin, D., & Li, Y. (2023) · arXiv · doi:10.48550/arxiv.2307.14984 · Cited by 10
ChatMOF: An Autonomous AI System for Predicting and Generating Metal-Organic Frameworks
Kang, Y., & Kim, J. (2023) · arXiv · doi:10.48550/arxiv.2308.01423 · Cited by 10 · cited 2×
“This limitation mainly arises from two challenges [305].”
A Variational Basis for the Regulation and Structuration Mechanisms of Agent Societies
Costa, A. C. D. R. (2019) · Springer eBooks · doi:10.1007/978-3-030-16335-8 · Cited by 9 · cited 2×
“In this article, we characterize that the “Agent Society” refers to an open, persistent, situated, and organized framework [399] where LLM-based agents interact with each other in a defined environment.”
Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft
Kanitscheider, I., Huizinga, J., Farhi, D., Guss, W. H., Houghton, B., Sampedro, R., Zhokhov, P., Baker, B., Ecoffet, A., Tang, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2106.14876 · Cited by 9
Is There Any Social Principle for LLM-Based Agents?Preprint
Bai, J., Zhang, S., & Chen, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.11136 · Cited by 9
CAPE: Corrective Actions from Precondition Errors using Large Language ModelsPreprint
Raman, S. S., Cohen, V., Idrees, I., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.09935 · Cited by 9
Wilson, A. C., & Bishop, D. (2019) · Wellcome Open Research · doi:10.12688/wellcomeopenres.15210.1 · Cited by 8
RET-LLM: Towards a General Read-Write Memory for Large Language Models
Modarressi, A., Imani, A., Fayyaz, M., & Schütze, H. (2023) · arXiv · doi:10.48550/arxiv.2305.14322 · Cited by 8 · cited 1×
“Another approach translates sentences into triplet configurations [141], while some perceive memory as a unique data object, fostering varied interactions [142].”
Improving cross-task generalization with step-by-step instructions
Wu, Y., Zhao, Y., Li, Z., Qin, B., & Xiong, K. (2025) · Science China Information Sciences · doi:10.1007/s11432-023-3911-2 · Cited by 8
Phelps, S., & Russell, Y. I. (2025) · Journal of Physics: Complexity · doi:10.1088/2632-072x/ada711 · Cited by 8
Emotional Intelligence of Large Language Models
Wang, X., Li, X., Yin, Z., Wu, Y., & Jia, L. (2023) · arXiv · doi:10.48550/arxiv.2307.09042 · Cited by 8
Self-citationSoundSpaces: Audio-Visual Navigation in 3D EnvironmentsPreprint
Chen, C., Jain, U., Schissler, C., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.11474 · Cited by 7
Mehta, N., Teruel, M., Sanz, P. F., Deng, X., Awadallah, A. H., & Kiseleva, J. (2023) · arXiv · doi:10.48550/arxiv.2304.10750 · Cited by 7 · cited 2×
“In some studies, agents can autonomously judge whether the conversation is proceeding smoothly and seeking feedback when encountering errors [364, 365].”
Plan, Eliminate, and Track - Language Models are Good Teachers for Embodied Agents
Wu, Y., Min, S. Y., Bisk, Y., Salakhutdinov, R., Azaria, A., Li, Y., Mitchell, T., & Prabhumoye, S. (2023) · arXiv · doi:10.48550/arxiv.2305.02412 · Cited by 7 · cited 5×
“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.”
InfluentialInterAct: Exploring the Potentials of ChatGPT as a Cooperative Agent
Chen, P.-L., & Chang, C.-S. (2023) · arXiv · doi:10.48550/arxiv.2308.01552 · Cited by 7
Zhou, E., Zheng, R., Xi, Z., Gao, S., Fan, X., Fei, Z., Ye, J., Gui, T., Zhang, Q., & Huang, X. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.688 · Cited by 7
Self-citationTraining-Free Layout Control with Cross-Attention GuidancePreprint
Chen, M., Laina, I., & Vedaldi, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.03373 · Cited by 7
Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
Zheng, L., Wang, R., Wang, X., & An, B. (2023) · arXiv · doi:10.48550/arxiv.2306.07863 · Cited by 7
Self-citationXu, J., Ung, M., Komeili, M., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.03270 · Cited by 6 · cited 1×
“Xu et al. [361] compared various types of feedback and observed that combining multiple types of feedback can yield better results.”
Gentopia: A Collaborative Platform for Tool-Augmented LLMs
Xu, B., Liu, X., Shen, H., Han, Z., Li, Y., Yue, M., Peng, Z., Liu, Y., Yao, Z., & Xu, D. (2023) · arXiv · doi:10.48550/arxiv.2308.04030 · Cited by 6 · cited 1×
“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].”
Self-citationUnveiling factuality and injecting knowledge for LLMs via reinforcement learning and data proportion
Ke, W., Shang, Z., Luo, Z., Wang, P., Guo, Y., Liu, Q., & Chen, Y. (2024) · Science China Information Sciences · doi:10.1007/s11432-024-4158-4 · Cited by 6 · cited 1×
“For instance, Ke et al. [548] proposed a comprehensive approach to unveil factuality and inject knowledge through reinforcement learning and data proportion.”
User Behavior Simulation with Large Language Model based Agents
Wang, L., Zhang, J., Yang, H., Chen, Z., Tang, J., Zhang, Z., Chen, X., Lin, Y., Song, R., Zhao, W. X., et al. (2023) · arXiv · doi:10.48550/arxiv.2306.02552 · Cited by 6 · cited 1×
“In addition, there are also a number of noteworthy studies, e.g., using simulated societies to collect synthetic datasets [89,440,441], helping people to simulate rare yet difficult interpersonal situations [442,443].”
Self-citationSCM: Enhancing Large Language Model with Self-Controlled Memory Framework
Wang, B., Liang, X., Yang, J., Huang, H., Wu, S., Wu, P., Lu, L., Ma, Z., & Li, Z. (2023) · arXiv · doi:10.48550/arxiv.2304.13343 · Cited by 5 · cited 1×
“Using prompts, some methods succinctly integrate memories [135], while others emphasize reflective processes to create condensed memory representations [16,136].”
Dagan, G., Keller, F., & Lascarides, A. (2023) · arXiv · doi:10.48550/arxiv.2308.06391 · Cited by 5
Mind meets machine: Unravelling GPT-4's cognitive psychologyPreprint
Dhingra, S., Singh, M. M., Vaisakh, S. B., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.11436 · Cited by 5
DISCOVERIES IN THE HUMAN BRAIN. NEUROSCIENCE PREHISTORY, BRAIN STRUCTURE, AND FUNCTION.
Haas, L. J. (1999) · Brain · doi:10.1093/brain/122.4.785 · Cited by 4
Chat with the Environment: Interactive Multimodal Perception Using Large Language ModelsPreprint
Zhao, X., Li, M., Weber, C., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.08268 · Cited by 4
RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs
Akyürek, A. F., Akyürek, E., Madaan, A., Kalyan, A., Clark, P., Wijaya, D., & Tandon, N. (2023) · arXiv · doi:10.48550/arxiv.2305.08844 · Cited by 4
Math Agents: Computational Infrastructure, Mathematical Embedding, and Genomics
Swan, M., Kido, T., Roland, E., & Santos, R. P. D. (2023) · arXiv · doi:10.48550/arxiv.2307.02502 · Cited by 4 · cited 1×
“Agents can also aid in human understanding and utilization of mathematics [369].”
Characterizing the Impacts of Instances on Robustness
Zheng, R., Xi, Z., Liu, Q., Lai, W., Gui, T., Zhang, Q., Huang, X., Ma, J., Shan, Y., & Ge, W. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.146 · Cited by 4
Self-citationLandmark Attention: Random-Access Infinite Context Length for Transformers
Mohtashami, A., & Jaggi, M. (2023) · arXiv · doi:10.48550/arxiv.2305.16300 · Cited by 4
Grounding Open-Domain Instructions to Automate Web Support TasksPreprint
Xu, N., Masling, S., Du, M., Campagna, G., Heck, L. P., Landay, J. A., & Lam, M. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.16057 · Cited by 3 · cited 1×
“In this way, agents can achieve accessibility and automation when dealing with unseen tasks in the future [298], freeing humans from repeated interactions with computer UIs.”
Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an IdentityPreprint
Shuster, K., Urbanek, J., Szlam, A. D., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.05843 · Cited by 3 · cited 1×
“Furthermore, agents should maintain their identities and avoid unnecessary confusion when engaged in long-term tasks [16,89,495].”
Decision-Oriented Dialogue for Human-AI CollaborationPreprint
Lin, J., Tomlin, N., Andreas, J., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.20076 · Cited by 3 · 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].”
Liang, Y., Zhu, L., & Yang, Y. (2023) · arXiv · doi:10.48550/arxiv.2307.12573 · Cited by 3 · cited 1×
“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].”
ProAgent: Building Proactive Cooperative Agents with Large Language ModelsPreprint
Zhang, C., Yang, K., Hu, S., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.11339 · Cited by 3 · cited 1×
“(1) Positive group behaviors foster collective well-being [16, 90, 322, 327, 328, 340].”
Heterogeneous Value Alignment Evaluation for Large Language ModelsPreprint
Zhang, Z., Zhang, C., Liu, N., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.17147 · Cited by 3
CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language ModelsPreprint
Qian, C., Han, C., Fung, Y. R., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.14318 · Cited by 3 · cited 1×
“Previous studies showed that LLM-based agents not only have the ability to generalize the use of existing tools, but can also make new tools they need by generating executable programs, or integrating existing tools into more powerful ones [75,241,242].”
Kwon, D., Lee, S., Kim, K. H., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.03361 · Cited by 2 · cited 1×
“Techniques like prompt engineering [16,430] and personality-enriched datasets [431,432] are used to optimize LLMs and train them to exhibit specific personality traits.”
Knowledge-enhanced Agents for Interactive Text Games
Chhikara, P., Zhang, J., Ilievski, F., Francis, J., & Ma, K. (2023) · Proceedings of the 12th Knowledge Capture Conference 2023 · doi:10.1145/3587259.3627561 · Cited by 2 · 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].”
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) · arXiv · doi:10.48550/arxiv.2401.10019 · Cited by 2 · cited 1×
“To safeguard against these risks, Yuan et al. [559] introduced R-judge, a benchmark designed to assess the proficiency of LLMs to judge and identify safety risks given agent interaction records.”
Towards Autonomous Testing Agents via Conversational Large Language ModelsPreprint
FELDT, R. H., Kang, S., Yoon, J., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.05152 · Cited by 2 · cited 2×
“Experts from the computer field make full use of the agent’s powerful code comprehension and debugging abilities [288,311].”
Theory of Mind Based Assistive Communication in Complex Human Robot CooperationPreprint
Buehler, M. C., Adamy, J., & Weisswange, T. H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.01355 · Cited by 2
Memory Sandbox: Transparent and Interactive Memory Management for Conversational AgentsPreprint
Huang, Z., Gutierrez, S., Kamana, H., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.01542 · Cited by 1 · 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].”
Zhou, E., Zheng, R., Xi, Z., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.11227 · Cited by 1 · cited 1×
“Moreover, agents express opinions and broadcast information to interact with others [332,405].”
Self-citationExamining the Inter-consistency of large language models: An in-depth analysis via debate
XIONG, K., DING, X., CAO, Y., LIU, T., & Bing, Q. I. N. (2023) · Singapore Management University Institutional Knowledge (InK) (Singapore Management University) · Cited by 1
Generating Executable Action Plans with Environmentally-Aware Language ModelsPreprint
Gramopadhye, M., & Szafir, D. J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.04964
Hey Dona! Can you help me with student course registration?Preprint
Kalvakurthi, V., Varde, A. S., & Jenq, J. J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.13548 · cited 2×
“Currently, LLM-powered autonomous agents primarily function as human assistants, accepting tasks delegated by humans to either independently complete assignments or assist in human task completion [95,167,300,311,367,376].”
Bharadhwaj, H., Vakil, J., Sharma, M. K., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.01918
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Workshop, B., :, Scao, T. L., Fan, A., Akiki, C., Pavlick, E., Ilić, S., Hesslow, D., Castagné, R., Luccioni, A. S., et al. (2022) · arXiv · doi:10.48550/arxiv.2211.05100
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
Longpre, S., Hou, L., Vu, T., Webson, A., Chung, H. W., Tay, Y., Zhou, D., Le, Q. V., Zoph, B., Wei, J., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.13688
Towards Healthy AI: Large Language Models Need Therapists Too
Lin, B., Bouneffouf, D., Cecchi, G., & Varshney, K. R. (2023) · arXiv · doi:10.48550/arxiv.2304.00416
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
Maaz, M., Rasheed, H., Khan, S., & Khan, F. S. (2023) · arXiv · doi:10.48550/arxiv.2306.05424 · cited 1×
“Moreover, the projection layer can effectively integrate with the learnable interface to adapt the dimensions of its outputs, making them compatible with LLMs [214–217].”
OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.08774
Self-citationLin, Y.-T., & Chen, Y.-N. (2023) · arXiv · doi:10.48550/arxiv.2305.13711
A Tutorial on Meta-Reinforcement Learning
Beck, J., Vuorio, R., Liu, E. Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.08028
A Survey on Multimodal Large Language Models
Yin, S., Fu, C., Zhao, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2306.13549
On the Creativity of Large Language Models
Franceschelli, G., & Musolesi, M. (2023) · arXiv · doi:10.48550/arxiv.2304.00008 · cited 1×
“Furthermore, they can showcase autonomy through exhibiting creativity like coming up with novel ideas, stories, or solutions that have not been explicitly programmed into them [97,98].”
SAPIEN: Affective Virtual Agents Powered by Large Language Models
Hasan, M., Ozel, C., Potter, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.03022
Policy Transfer using Reward Shaping
Brys, T., Harutyunyan, A., Taylor, M. E., & Nowé, A. (2015) · International Joint Conference on Autonomous Agents and Multiagent Systems · doi:10.65109/junf6077 · cited 1×
“Consequently, researchers introduce transfer learning to expedite an agent’s learning on new tasks [57–59].”
Meshed-Memory Transformer for Image Captioning
Cornia, M., Stefanini, M., Baraldi, L., & Cucchiara, R. (2019) · arXiv · doi:10.48550/arxiv.1912.08226
Dorbala, V. S., Mullen, J. F., & Manocha, D. (2023) · arXiv · doi:10.48550/arxiv.2303.03480 · cited 1×
“A memory mechanism is needed to record historical information [277], which is also adopted in Smallville and Voyager [16, 177,278, 279].”
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) · arXiv · doi:10.48550/arxiv.2204.03685
DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
Moravčík, M., Schmid, M., Burch, N., Lisý, V., Morrill, D., Bard, N., Davis, T., Waugh, K., Johanson, M., & Bowling, M. (2017) · arXiv · doi:10.48550/arxiv.1701.01724 · cited 1×
“While agents have already excelled in pure competitive environments like chess [335], Go [50], and poker [391], LLM-based agents go further by devising unified cooperative strategies through effective negotiation and collaboration in more complex scenarios [392–395].”
Automated Agent Decomposition for Classical Planning
Crosby, M., Rovatsos, M., & Petrick, R. (2013) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v23i1.13564 · cited 1×
“Through reasoning, agents break down complex tasks into manageable sub-tasks, devising appropriate plans for each [161, 162].”
MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Fan, L., Wang, G., Jiang, Y., et al. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1333
Extracting Training Data from Diffusion Models
Carlini, N., Hayes, J., Nasr, M., Jagielski, M., Sehwag, V., Tramèr, F., Balle, B., Ippolito, D., & Wallace, E. (2023) · arXiv · doi:10.48550/arxiv.2301.13188
2. ACTIONS, REASONS, AND CAUSES
Davidson, D. (n.d.) · Causal Theories of Mind · doi:10.1515/9783110843828.58
Software-Based Dialogue Systems: Survey, Taxonomy and Challenges
Motger, Q., Franch, X., & Marco, J. (2021) · arXiv · doi:10.48550/arxiv.2106.10901 · cited 1×
“With the rapid development of AI, conversational agents have garnered extensive attention in various forms [377] and in various scenarios [378–380].”
Advances in adversarial attacks and defenses in computer vision: A survey
Akhtar, N., Mian, A., Kardan, N., & Shah, M. (2021) · arXiv · doi:10.48550/arxiv.2108.00401 · cited 2×
“It has been extensively explored in fields such as computer vision [500,503–505], natural language processing [506–509], and reinforcement learning [510–512], and has remained a pivotal factor in determining the applicability of deep learning systems [513–515].”
Knowledge-enhanced Agents for Interactive Text Games
Chhikara, P., Zhang, J., Ilievski, F., Francis, J., & Ma, K. (2023) · arXiv · doi:10.48550/arxiv.2305.05091 · 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].”
Using cognitive psychology to understand GPT-3
Binz, M., & Schulz, E. (2022) · arXiv · doi:10.48550/arxiv.2206.14576 · cited 2×
“They conducted psychology experiments about judgment and decision-making to test agent systems [413, 414, 416, 417].”
Improved Automatic Keyword Extraction Given More Semantic Knowledge
Yang, K., Chen, Z., Cai, Y., Huang, D., & Leung, H.-F. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-32055-7_10
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.