The rise and potential of large language model based agents: a survey
Open accessThe DOI matches its Crossref record; 706 of the 706 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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In 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]
Experimental — accuracy not yet measuredThe 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 measured
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 2×
“Deep neural networks have garnered significant attention for their remarkable performance across various tasks [69,183,538].”
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 4×
“Deep neural networks have garnered significant attention for their remarkable performance across various tasks [69,183,538].”
InfluentialArtificial intelligence: a modern approach
(1995) · Choice Reviews Online · doi:10.5860/choice.33-1577 · Cited by 21,974
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · cited 4×
“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].”
InfluentialReceptive fields, binocular interaction and functional architecture in the cat’s visual cortex
Hubel, D. H., & Wiesel, T. N. (1962) · The Journal of Physiology · doi:10.1113/jphysiol.1962.sp006837 · Cited by 13,680
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
The NIST definition of cloud computing
Mell, P. M., & Grance, T. (2011) · doi:10.6028/nist.sp.800-145 · Cited by 11,795
Proceedings of the 24th international conference on Machine learning
(2007) · doi:10.1145/1273496 · Cited by 11,630
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 1×
“Deep neural networks have garnered significant attention for their remarkable performance across various tasks [69,183,538].”
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
Items 1,001–1,024 of 1,024
KwaiAgents: Generalized Information-seeking Agent System with Large Language Models
Pan, H., Zhai, Z., Yuan, H., Lv, Y., Fu, R., Liu, M., Wang, Z., & Qin, B. (2023) · arXiv · doi:10.48550/arxiv.2312.04889 · Cited by 1
Fundamentals of Building Autonomous LLM Agents
Castrillo, V. D. L., Gidey, H. K., Lenz, A., & Knoll, A. (2025) · arXiv · doi:10.48550/arxiv.2510.09244 · Cited by 1
GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-Based VLM Agent Training
Wei, T., Yang, Y., Xing, J., Shi, Y., Lu, Z., & Ye, D. (2025) · 2025 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01752 · Cited by 1
GIEBench: Towards Holistic Evaluation of Group Identity-based Empathy for Large Language Models
Wang, L., Jin, Y., Shen, T., Zheng, T., Du, X., Zhang, C., Huang, W., Liu, J., Wang, S., Zhang, G., et al. (2024) · arXiv · doi:10.48550/arxiv.2406.14903 · Cited by 1
Jin, Y., Martinez‐Maldonado, R., Gašević, D., Han, X., & Yan, L. (2026) · Journal of Computer Assisted Learning · doi:10.1002/jcal.70310 · Cited by 1
“In higher education and professional settings, AI systems are shifting from passive tools to active participants embedded within collaborative processes (Kamalov et al., 2025; Sapkota, Roumeliotis, & Karkee, 2025; Xi et al., 2025).”
Gómez Álvarez, S., Mozo Quesada, A., Navarro, T., Gálvez Rojas, S., & López Valverde, F. (2026) · Journal of Intelligent Information Systems · doi:10.1007/s10844-026-01086-z · Cited by 1
“Similarly, Xi et al. (2025) proposed a multidimensional framework that encompasses four axes: practical utility, social cooperation with humans and other agents, value alignment, and adaptive evolution, capturing both immediate performance and long-term autonomy.”
Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges
Motger, Q., Oriol, M., Marco, J., & Franch, X. (2026) · arXiv · doi:10.48550/arxiv.2607.26212 · Cited by 5
Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration
Xu, J., Wu, X., Zhang, Z., Xu, Y., Yang, Y., Zhu, J., Xiao, L., Wu, W., & He, L. (2026) · arXiv · doi:10.48550/arxiv.2606.18259
Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents
La Malfa, G., Meegahapola, L., Bogucka, E., Zhang, J. M., Luck, M., Black, E., & Quercia, D. (2026) · arXiv · doi:10.48550/arxiv.2608.08601
A Comment On "The Illusion of Thinking": Reframing the Reasoning Cliff as an Agentic Gap
Khan, S., Madhavan, S., & Natarajan, K. (2025) · arXiv · doi:10.48550/arxiv.2506.18957
SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
Kutasov, J., Sun, Y., Colognese, P., van der Weij, T., Petrini, L., Zhang, C. B. C., Hughes, J., Deng, X., Sleight, H., Tracy, T., et al. (2025) · arXiv · doi:10.48550/arxiv.2506.15740
Ctrl-Z: Controlling AI Agents via Resampling
Bhatt, A., Rushing, C., Kaufman, A., Tracy, T., Georgiev, V., Matolcsi, D., Khan, A., & Shlegeris, B. (2025) · arXiv · doi:10.48550/arxiv.2504.10374
AutoMind: Adaptive Knowledgeable Agent for Automated Data Science
Luo, Y., Ou, Y., Zheng, J., Wei, L., Yu, Z., Qiao, S., Zhang, J., Zheng, D., Mao, Y., Gao, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2506.10974
Yang, H., Chen, J., Siew, M., Lorido-Botran, T., & Joe-Wong, C. (2025) · arXiv · doi:10.48550/arxiv.2502.05453
Permissive Information-Flow Analysis for Large Language Models
Siddiqui, S. A., Gaonkar, R., Köpf, B., Krueger, D., Paverd, A., Salem, A., Tople, S., Wutschitz, L., Xia, M., & Zanella-Béguelin, S. (2024) · arXiv · doi:10.48550/arxiv.2410.03055
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
AGI Team, Cai, Y., Chen, L., Chen, Q., Ding, Y., Fan, L., Fu, W., Gao, Y., Guo, H., Guo, P., et al. (2025) · arXiv · doi:10.48550/arxiv.2512.04987
Self-citationSafety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Lin, R., Deng, X., Li, Q., Ma, J., Feng, Y., Qing, Y., Li, Z., Zhang, Y., Cui, S., Meng, C., et al. (2026) · arXiv · doi:10.48550/arxiv.2606.23075
Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective
Wadlom, N., Shen, J., & Lu, Y. (2026) · Proceedings of the ACM on Management of Data · doi:10.1145/3802046
Barbaste, P., Darrigol, T., Vu, G., & Wiltberger, T. (2026) · arXiv · doi:10.48550/arxiv.2609.00006
DataEvolver: Automatic Data Preparation for Large Language Models through Multi-Level Self-Evolving
Deng, C., Zhang, S., Fan, J., & Du, X. (2026) · arXiv · doi:10.48550/arxiv.2606.07001
PaperRepro: Automated Computational Reproducibility Assessment for Social Science Papers
Zhang, L., Xia, T., Piao, J., & Cui, L. (2026) · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · doi:10.1145/3770855.3818943
Accurate and Efficient Long-Term Memory for LLM Agents
Zhao, Z., Guo, X., Lv, L., Wang, M., Li, M., & Li, S. (2026) · arXiv · doi:10.48550/arxiv.2607.16211
Self-citation
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.