CoChat

From language to action: a review of large language models as autonomous agents and tool users

Open access

The DOI matches its Crossref record; 130 of the 130 references it cites were found in a registry or an index.

Abstract

The pursuit of human-level artificial intelligence (AI) has significantly advanced the development of autonomous agents and Large Language Models (LLMs). LLMs are now widely utilized as decision-making agents for their ability to interpret instructions, manage sequential tasks, and adapt through feedback. This review examines recent developments in employing LLMs as autonomous agents and tool users and comprises seven research questions. We only used the papers published between 2023 and 2025 in conferences of the A* and A-ranked and Q1 journals. A structured analysis of the LLM agents’ architectural design principles, dividing their applications into single-agent and multi-agent systems, and strategies for integrating external tools is presented. In addition, the cognitive mechanisms of LLMs, including reasoning, planning, and memory, and the impact of prompting methods and fine-tuning procedures on agent performance are also investigated. Furthermore, we have evaluated current benchmarks and assessment protocols and provided an analysis of 68 publicly available datasets to assess the performance of LLM-based agents in various tasks. In conducting this review, we have identified critical findings on verifiable reasoning of LLMs, the capacity for self-improvement, and the personalization of LLM-based agents. Finally, we have discussed ten future research directions to overcome these gaps.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s10462-025-11471-9

Cites

130 of 130 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Research works printed but not linked: 93

  1. Arumugam D, Griffiths TL (2025) Toward efficient exploration by large language model agents. In: The exploration in AI today workshop at ICML 2025
  2. Austin J, Odena A, Nye M, Bosma M, Michalewski H et al (2021) Program synthesis with large language models. arXiv preprint arXiv:2108.07732 · arXiv
  3. Bai Y, Jones A, Ndousse K, Askell A, Chen A et al (2022) Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 · arXiv
  4. Bai X, Huang S, Wei C, Wang R (2025) Collaboration between intelligent agents and large language models: a novel approach for enhancing code generation capability. Expert Syst Appl 269:126357
  5. Bhardwaj R, Poria S (2023) Red-teaming large language models using chain of utterances for safety-alignment. arXiv preprint arXiv:2308.09662 · arXiv
  6. Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877–1901
  7. Cai Y, Li X, Goswami M, Wiliński M, Welter G, Dubrawski A (2025) LLM agents struggle at time series machine learning engineering. In: 1st ICML Workshop on foundation models for structured data
  8. Chang M, Zhang J, Zhu Z, Yang C, Yang Y, Jin Y, Lan Z, Kong L, He J (2024) Agentboard: An analytical evaluation board of multi-turn llm agents. Adv Neural Inf Process Syst 37:74325–74362
  9. Chen M, Tworek J, Jun H, Yuan Q et al (2021) Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 · arXiv
  10. Chen J, Yu C, Zhou X, Xu T, Mu Y, et al (2025c) Emos: Embodiment-aware heterogeneous multi-robot operating system with llm agents. arXiv preprint arXiv:2410.22662v2 · arXiv
  11. Cheng J, Chin P (2024) Sociodojo: Building lifelong analytical agents with real-world text and time series. In: The twelfth international conference on learning representations
  12. Cheng Y, Zhang C, Zhang Z, Meng X, Hong S, et al (2024) Exploring large language model based intelligent agents: definitions, methods, and prospects. arXiv preprint arXiv:2401.03428 · arXiv
  13. Cobbe K, Kosaraju V, Bavarian M, Chen M, Jun H et al (2021) Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 · arXiv
  14. Dasari S, Ebert F, Tian S, Nair S, Bucher B et al (2019) Robonet: Large-scale multi-robot learning. arXiv preprint arXiv:1910.11215 · arXiv
  15. Deng X, Gu Y, Zheng B, Chen S, Stevens S et al (2023) Mind2web: Towards a generalist agent for the web. Adv Neural Inf Process Syst 36:28091–28114
  16. Driess D, Xia F, Sajjadi MSM, Lynch C, Chowdhery A et al (2023) Palm-e: An embodied multimodal language model. arXiv preprint arXiv:2303.03378 · arXiv
  17. Ferrag MA, Tihanyi N, Debbah M (2025) From llm reasoning to autonomous ai agents: a comprehensive review. arXiv preprint arXiv:2504.19678 · DOI · Paper page
  18. Fu Y, Kim D-K, Kim J, Sohn S, Logeswaran L et al (2024) Autoguide: Automated generation and selection of context-aware guidelines for large language model agents. Adv Neural Inf Process Syst 37:119919–119948
  19. Hendrycks D, Burns C, Basart S, Zou A, Mazeika M et al (2021) Measuring massive multitask language understanding. In: Proceedings of the international conference on learning representations (ICLR)
  20. Hong S, Zhuge M, Chen J, Zheng X, Cheng Y et al (2023) Metagpt: Meta programming for a multi-agent collaborative framework. In: The twelfth international conference on learning representations
  21. Huang Q, Vora J, Liang P, Leskovec J (2023) Benchmarking large language models as ai research agents. In: NeurIPS 2023 foundation models for decision making workshop
  22. Ji J, Liu M, Dai J, Pan X, Zhang C et al (2023) Beavertails: Towards improved safety alignment of llm via a human-preference dataset. Adv Neural Inf Process Syst 36:24678–24704
  23. Jin Y, Ma J (2024) Large language model as parking planning agent in the context of mixed period of autonomous vehicles and human-driven vehicles. Sustain Cities Soc 117:105940
  24. Kang J, Laroche R, Yuan X, Trischler A, Liu X, Fu J (2024) Think before you act: Decision transformers with working memory. arXiv preprint arXiv:2305.16338v3 · arXiv
  25. Kapitanov A, Kvanchiani K, xNagaev K, Kraynov R, Makhliarchuk A (2024) Hagrid – hand gesture recognition image dataset. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision (WACV), pp 4572–4581
  26. Khan MA, Amani M, Das S, Ghosh B, Wu Q et al (2025) In agents we trust, but who do agents trust? latent source preferences steer LLM generations. In: ICML 2025 workshop on reliable and responsible foundation models
  27. Kim Y, Park C, Jeong H, Chan YS, Xu X et al (2024) Mdagents: An adaptive collaboration of llms for medical decision-making. Adv Neural Inf Process Syst 37:79410–79452
  28. Klein LH, Potamitis N, Aydin R, West R, Gulcehre C, Arora A (2025) Fleet of agents: coordinated problem solving with large language models. In: Forty-second international conference on machine learning
  29. Köpf A, Kilcher Y, Von Rütte D, Anagnostidis S, Tam ZR et al (2023) Openassistant conversations-democratizing large language model alignment. Adv Neural Inf Process Syst 36:47669–47681
  30. Lampinen A, Chan S, Dasgupta I, Nam A, Wang J (2023) Passive learning of active causal strategies in agents and language models. Adv Neural Inf Process Syst 36:1283–1297
  31. Li X (2025) A review of prominent paradigms for llm-based agents: tool use, planning (including rag), and feedback learning. In: Proceedings of the 31st international conference on computational linguistics, pp 9760–9779
  32. Li XL, Chowdhury N, Johnson DD, Hashimoto T, Liang P, et al (2025a) Eliciting language model behaviors with investigator agents. In: Forty-second international conference on machine learning
  33. Li Z, Zhang R, Wang Z, Xie Z, Song Y (2025b) Llm-guided decision-making toolkit for multi-agent reinforcement learning. Neurocomputing 638:130105
  34. Liu T, Xu C, McAuley J (2023) Repobench: Benchmarking repository-level code auto-completion systems. arXiv preprint arXiv:2306.03091 · arXiv
  35. Liu Z, Hu H, Zhang S, Guo H, Ke S, et al (2024a) Reason for future, act for now: a principled architecture for autonomous LLM agents. In: Proceedings of the 41st international conference on machine learning, ser. Proceedings of Machine Learning Research, vol. 235. PMLR, pp 31 186–31 261
  36. Liu R, Yang R, Jia C, Zhang G, Yang D, Vosoughi S (2024b) Training socially aligned language models on simulated social interactions. In: The twelfth international conference on learning representations
  37. Liu X, Yu H, Zhang H, Xu Y, Lei X et al (2024c) Agentbench: Evaluating LLMs as agents. In: The twelfth international conference on learning representations
  38. Liu X, ZHANG J, Shang H, Guo S, Chengxu Y, Zhu Q (2025b) Exploring prosocial irrationality for LLM agents: a social cognition view. In: The thirteenth international conference on learning representations
  39. Lu P, Qiu L, Chang KW, Wu YN, Zhu SC et al (2023) Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning. In: International conference on learning representations (ICLR)
  40. Luo J, Zhang W, Yuan Y, Zhao Y, Yang J et al (2025) Large language model agent: a survey on methodology, applications and challenges. arXiv preprint arXiv:2503.21460 · arXiv
  41. Ma H, Hu T, Pu Z, Boyin L, Ai X et al (2024) Coevolving with the other you: fine-tuning LLM with sequential cooperative multi-agent reinforcement learning. Adv Neural Inf Process Syst 37:15497–15525
  42. Ni B, Buehler MJ (2024) Mechagents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge. Extreme Mech Lett 67:102131
  43. Ning Y, Liu H (2024) Urbankgent: A unified large language model agent framework for urban knowledge graph construction. Adv Neural Inf Process Syst 37:123127–123154
  44. Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C et al (2022) Training language models to follow instructions with human feedback. Adv Neural Inf Process Syst 35:27730–27744
  45. Pang J-C, Yang S-H, Li K, Zhang J, Chen X-H et al (2024a) Kalm: Knowledgeable agents by offline reinforcement learning from large language model rollouts. Adv Neural Inf Process Syst 37:126620–126652
  46. Penedo G, Kydlíček H, allal LB, Lozhkov A, Mitchell M et al (2024) The fineweb datasets: Decanting the web for the finest text data at scale. In: The thirty-eight conference on neural information processing systems datasets and benchmarks track
  47. Qiao S, Fang R, Zhang N, Zhu Y, Chen X et al (2024a) Agent planning with world knowledge model. Adv Neural Inf Process Syst 37:114843–114871
  48. Qin Y, Liang S, Ye Y, Zhu K, Yan L et al (2024b) ToolLLM: Facilitating large language models to master 16000+ real-world APIs. In: The twelfth international conference on learning representations
  49. Qu Y, Zhang T, Garg N, Kumar A (2024) Recursive introspection: teaching language model agents how to self-improve. Adv Neural Inf Process Syst 37:55249–55285
  50. Ruan Y, Dong H, Wang A, Pitis S, Zhou Y et al (2024) Identifying the risks of LM agents with an LM-emulated sandbox. In: The twelfth international conference on learning representations
  51. Schick T, Dwivedi-Yu J, Dessì R, Raileanu R, Lomeli M et al (2023) Toolformer: Language models can teach themselves to use tools. Adv Neural Inf Process Syst 36:68539–68551
  52. Schumann R, Zhu W, Feng W, Fu T-J, Riezler S, Wang WY (2024) Velma: Verbalization embodiment of llm agents for vision and language navigation in street view. Proc AAAI Conf Artif Intell 38(17):18924–18933
  53. Shinn N, Cassano F, Gopinath A, Narasimhan K, Yao S (2023) Reflexion: Language agents with verbal reinforcement learning. Adv Neural Inf Process Syst 36:8634–8652
  54. Shi F, Suzgun M, Freitag M, Wang X, Srivats S et al (2022) Language models are multilingual chain-of-thought reasoners. arXiv preprint arXiv:2210.03057 · arXiv
  55. Shridhar M, Yuan X, Côté MA, Bisk Y, Trischler A, Hausknecht M (2021) ALFWorld: aligning text and embodied environments for interactive learning. In: Proceedings of the international conference on learning representations (ICLR)
  56. Talebirad Y, Nadiri A (2023) Multi-agent collaboration: Harnessing the power of intelligent llm agents. arXiv preprint arXiv:2306.03314 · arXiv
  57. Tennant E, Hailes S, Musolesi M (2025) Moral alignment for LLM agents. In: The thirteenth international conference on learning representations
  58. Valmeekam K, Marquez M, Olmo A, Sreedharan S, Kambhampati S (2023) Planbench: An extensible benchmark for evaluating large language models on planning and reasoning about change. Adv Neural Inf Process Syst 36:38975–38987
  59. Walke HR, Black K, Zhao TZ, Vuong Q, Zheng C et al (2023) Bridgedata v2: A dataset for robot learning at scale. In: Conference on robot learning. PMLR, pp 1723–1736
  60. Wang P, Li L, Shao Z, Xu R, Dai D et al (2023b) Math-shepherd: Verify and reinforce llms step-by-step without human annotations. arXiv preprint arXiv:2312.08935v3 · arXiv
  61. Wang G, Xie Y, Jiang Y, Mandlekar A, Xiao C et al (2023c) Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 · arXiv
  62. Wang Z, Zhang G, Yang K, Shi N, Zhou W et al (2023d) Interactive natural language processing. arXiv preprint arXiv:2305.13246 · arXiv
  63. Wang Z, Cai S, Mu Z, Lin H, Zhang C et al (2024a) Omnijarvis: Unified vision-language-action tokenization enables open-world instruction following agents. Adv Neural Inf Process Syst 37:73278–73308
  64. Wang L, Ma C, Feng X et al (2024b) A survey on large language model based autonomous agents. Front Comp Sci 18:186345
  65. Wang L, Zhang J, Yang H, Chen Z-Y, Tang J et al (2025b) User behavior simulation with large language model-based agents. ACM Trans Inform Syst 43(2):1–37
  66. Wang Z, Zhu Y, Zhao H, Zheng X, Sui D et al (2025c) Colacare: Enhancing electronic health record modeling through large language model-driven multi-agent collaboration. Proc ACM Web Conf 2025:2250–2261
  67. Weber M, Fu DY, Anthony Q, Oren Y, Adams S et al (2024) Redpajama: an open dataset for training large language models. NeurIPS Datasets and Benchmarks Track
  68. Wei J, Wang X, Schuurmans D, Bosma M, Ichter B et al (2022) Chain-of-thought prompting elicits reasoning in large language models. In: Proceedings of the 36th international conference on neural information processing systems, ser. NIPS ’22. Red Hook, NY, USA: Curran Associates Inc
  69. Wijk H, Lin T, Becker J, Jawhar S, Parikh N et al (2025) RE-bench: Evaluating frontier AI r &d capabilities of language model agents against human experts. In: Forty-second international conference on machine learning
  70. Wu S, Zhao S, Huang Q, Huang K, Yasunaga M et al (2024b) Avatar: Optimizing llm agents for tool usage via contrastive reasoning. Adv Neural Inf Process Syst 37:25981–26010
  71. Wu Q, Bansal G, Zhang J, Wu Y, Li B et al (2024c) Autogen: Enabling next-gen LLM applications via multi-agent conversations. In: First conference on language modeling
  72. Wu S, Zhao S, Yasunaga M, Huang K, Cao K et al (2024d) Stark: Benchmarking llm retrieval on textual and relational knowledge bases. In: NeurIPS datasets and benchmarks track
  73. Xi Z, Chen W, Guo X et al (2025) The rise and potential of large language model based agents: a survey. Sci China Inf Sci 68:121101
  74. Xia Y, Shen W, Wang Y, Liu JK, Sun H et al (2025) Leetcodedataset: A temporal dataset for robust evaluation and efficient training of code llms. arXiv preprint arXiv:2504.14655 · arXiv
  75. Xiang Z, Zheng L, Li Y, Hong J, Li Q et al (2025) Guardagent: safeguard LLM agents via knowledge-enabled reasoning. In: ICML 2025 workshop on computer use agents
  76. Xie C, Chen C, Jia F, Ye Z, Lai S et al (2024a) Can large language model agents simulate human trust behavior? Adv Neural Inf Process Syst 37:15674–15729
  77. Xu Y, Su H, Xing C, Mi B, Liu Q et al (2024b) Lemur: Harmonizing natural language and code for language agents. In: The twelfth international conference on learning representations
  78. Yang J, Prabhakar A, Narasimhan K, Yao S (2023) Intercode: Standardizing and benchmarking interactive coding with execution feedback. Adv Neural Inf Process Syst 36:23826–23854
  79. Yang W, Bi X, Lin Y, Chen S, Zhou J, Sun X (2024a) Watch out for your agents! investigating backdoor threats to llm-based agents. Adv Neural Inf Process Syst 37:100938–100964
  80. Yang Y, Zhou T, Li K, Tao D, Li L et al (2024d) Embodied multi-modal agent trained by an llm from a parallel textworld. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 26 275–26 285
  81. Yao S, Yu D, Zhao J, Shafran I, Griffiths T et al (2023a) Tree of thoughts: deliberate problem solving with large language models. Adv Neural Inf Process Syst 36:11809–11822
  82. Yao S, Zhao J, Yu D, Du N, Shafran I et al (2023b) React: Synergizing reasoning and acting in language models. In: International conference on learning representations (ICLR)
  83. Zhai S, Bai H, Lin Z, Pan J, Tong P et al (2024) Fine-tuning large vision-language models as decision-making agents via reinforcement learning. Adv Neural Inf Process Syst 37:110935–110971
  84. Zhang D, Chen L, Zhang S, Xu H, Zhao Z, Yu K (2023) Large language models are semi-parametric reinforcement learning agents. Adv Neural Inf Process Syst 36:78227–78239
  85. Zhang C, Yang K, Hu S, Wang Z, Li G et al (2024d) Proagent: building proactive cooperative agents with large language models. Proceedings AAAI Conf Artif Intell 38(16):17591–17599
  86. Zhang S, Dong Y, Zhang Y, Payne TR, Zhang J (2024e) Large language model assissted multi-agent dialogue for ontology alignment. In: Proceedings of the 23rd international conference on autonomous agents and multiagent systems, pp 2594–2596 · doi:10.65109/pxec2992
  87. Zhang H, Du W, Shan J, Zhou Q, Du Y et al (2024g) Building cooperative embodied agents modularly with large language models. In: The Twelfth international conference on learning representations
  88. Zhang S, Zhang J, Liu J, Song L, Wang C et al (2024k) Offline training of language model agents with functions as learnable weights. In: Proceedings of the 41st international conference on machine learning, ser. Proceedings of Machine Learning Research, vol. 235. PMLR, 21–27, pp 60315–60335
  89. Zhao Q, Wang J, Zhang Y, Jin Y, Zhu K, et al (2024b) CompeteAI: Understanding the competition dynamics of large language model-based agents. In: Proceedings of the 41st international conference on machine learning, ser. Proceedings of Machine Learning Research, vol. 235. PMLR, pp 61 092–61 107
  90. Zheng S, jiazheng liu, Feng Y, Lu Z (2024) Steve-eye: Equipping LLM-based embodied agents with visual perception in open worlds. In: The Twelfth international conference on learning representations
  91. Zhou H, Tang Y, Qin H, Yang Y, Jin R et al (2024) Star-agents: Automatic data optimization with llm agents for instruction tuning. Adv Neural Inf Process Syst 37:4575–4597
  92. Zhu F, Simmons R (2024) Bootstrapping cognitive agents with a large language model. Proc AAAI Conf Artif Intell 38(1):655–663
  93. Zou A, Wang Z, Carlini N, Nasr M, Kolter JZ, Fredrikson M (2023) Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043 · arXiv

Cited by

See all 51

Metadata

Authors
Chowa, S. S., Alvi, R., Rahman, S. S., Rahman, M. A., Raiaan, M. A. K., Islam, M. R., Hussain, M., & Azam, S.
Affiliations
  • Daffodil International University (BD)
  • United International University (BD)
  • Monash University (AU)
  • Charles Darwin University (AU)
Corresponding author
  • Raiaan, Mohaimenul Azam Khan
  • Azam, Sami
Venue
Artificial Intelligence Review
Published
2026-01-06
Volume
59
Issue
2
ISSN
  • 0269-2821 (ISSN-L)
  • 1573-7462
OpenAlex
W7118468219
Cited by
50
References
99
Citations by year
2026: 50
FWCI
169.75
Type
journal article
Language
en
Open access
Licence
Locations
  • Artificial Intelligence Review (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
Charles Darwin University
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
Keywords
large language models, autonomous agents, tool use, multi-agent systems, LLM agents, LLM reasoning, LLM memory, prompting, fine-tuning, benchmarking, human development, personalization, verifiable reasoning

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.