--- title: "A Survey on Large Language Model based — Wang 2023" description: "Classic autonomous agents were usually trained with simple policies inside small, closed environments, so they struggled to act in a humanlike way in…" authors: ["Lei Wang", "Chen Ma", "Xueyang Feng", "Zeyu Zhang", "Hao Yang", "Jingsen Zhang", "Zhiyuan Chen", "Jiakai Tang", "Xu Chen", "Yankai Lin", "Wayne Xin Zhao", "Zhewei Wei", "Ji-Rong Wen"] year: 2023 venue: "arXiv:2308.11432" source: "https://arxiv.org/abs/2308.11432" doi: "10.1007/s11704-024-40231-1" arxiv: "2308.11432" licence: "CC BY 4.0 (arXiv)" licence_url: "http://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/wang-2023-survey-large-language-model-based/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2023-survey-large-language-model-based/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/) / A Survey on Large Language Model based Autonomous Agents # A Survey on Large Language Model based Autonomous Agents **Authors:** [Lei Wang](https://md.research.elamur.ai/free/en/authors/lei-wang/), [Chen Ma](https://md.research.elamur.ai/free/en/authors/chen-ma/), Xueyang Feng, Zeyu Zhang, [Hao Yang](https://md.research.elamur.ai/free/en/authors/hao-yang/), Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, [Yankai Lin](https://md.research.elamur.ai/free/en/authors/yankai-lin/), [Wayne Xin Zhao](https://md.research.elamur.ai/free/en/authors/wayne-xin-zhao/), Zhewei Wei et al. (13 authors) · **Year:** 2023 · **Venue:** arXiv:2308.11432 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://doi.org/10.1007/s11704-024-40231-1) · [PDF](https://arxiv.org/pdf/2308.11432) · [DOI 10.1007/s11704-024-40231-1](https://doi.org/10.1007/s11704-024-40231-1) · [arXiv 2308.11432](https://arxiv.org/abs/2308.11432) · [OpenAlex](https://openalex.org/W4393065402) **Citations:** 1820 citations (openalex-snapshot · 2026-10-14) · [443](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary Classic autonomous agents were usually trained with simple policies inside small, closed environments, so they struggled to act in a humanlike way in open-ended settings. Large language models (LLMs) carry broad world knowledge from web-scale training, and this led to a fast-growing body of work that uses them as the core controller of an agent. This survey by Wang et al. reviews that work from three angles: how such agents are built, where they are used, and how they are evaluated. For building agents, the authors propose a single architecture made of four modules (profiling, memory, planning and action). They also sort methods for giving agents task skills by whether the underlying LLM is fine-tuned. The survey then covers uses in the social sciences, natural sciences and engineering. It compares subjective and objective ways of evaluating agents. It ends with open problems. Because most systems in this area were built in isolation, the survey's common taxonomy is a useful reference for anyone designing or comparing LLM-driven agents. ## Key points - **Four-module framework:** The profiling module sets the agent's role. The memory and planning modules let the agent use past experience and plan what to do next. The action module turns those decisions into outputs. Profiling shapes memory and planning, and all three feed into action. - **Ways to create agent profiles:** profiles can be written by hand (as in Generative Agent, MetaGPT and ChatDev), generated by an LLM, or aligned with real datasets. One example of the last approach gives GPT-3 personas based on demographic data from ANES respondents. - **Memory and planning:** Memory is described by its structure (unified or hybrid), its format (natural language, databases, embeddings or lists) and its operations (reading, writing and reflection). Planning is split into approaches that use feedback and those that don't. Feedback can come from the environment, a human or a model. - **Scope:** A growth chart counts papers published between January 2021 and August 2023. It groups them into categories such as tool, embodied, game, web, simulation and assistant agents (for example AutoGPT, Voyager and ToolBench). - **Open challenges:** These include alignment that still lets simulations reproduce negative human behaviour, fragile prompt frameworks, hallucination, LLMs knowing more than the humans they are meant to simulate, and slow inference when each action needs many LLM calls. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [AI & machine learning](https://md.research.elamur.ai/free/en/shelves/ai/) ## Cited by Cited by 443 papers of our library cite it (of the 140884 whose bibliographies we read); 22 of them have a page here, 421 not yet. - [基于大语言模型智能体的代码生成综述](https://md.research.elamur.ai/free/en/papers/dong-2025-code-generation-llm/) - [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://md.research.elamur.ai/free/en/papers/guo-2024-large-language-model-based/) - [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/) - [TrustLLM: Trustworthiness in Large Language Models](https://md.research.elamur.ai/free/en/papers/huang-2024-trustllm-trustworthiness-large-language-models/) - [A Survey on Large Language Models for Code Generation](https://md.research.elamur.ai/free/en/papers/jiang-2024-survey-large-language-models-code/) - [VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks](https://md.research.elamur.ai/free/en/papers/koh-2024-visualwebarena-evaluating-multimodal-agents-realistic/) - [LegalAgentBench: Evaluating LLM Agents in Legal Domain](https://md.research.elamur.ai/free/en/papers/li-2025-legalagentbench-evaluating-llm-agents-legal/) - [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://md.research.elamur.ai/free/en/papers/lu-2024-ai-scientist-fully-automated/) - [CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation](https://md.research.elamur.ai/free/en/papers/ma-2026-clase-hybrid-method-chinese-legalese/) - [A Comprehensive Overview of Large Language Models](https://md.research.elamur.ai/free/en/papers/naveed-2023-comprehensive-overview-large-language-models/) - [Large Language Diffusion Models](https://md.research.elamur.ai/free/en/papers/nie-2025-large-language-diffusion-models/) - [Designing LLM Agents for User-Centered Language Service Selection](https://md.research.elamur.ai/free/en/papers/ogawa-2026-designing-llm-agents-user-centered/) - [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://md.research.elamur.ai/free/en/papers/qi-2023-fine-tuning-aligned-language-models/) - [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://md.research.elamur.ai/free/en/papers/qin-2025-ui-tars-pioneering-automated/) - [Agent Laboratory: Using LLM Agents as Research Assistants](https://md.research.elamur.ai/free/en/papers/schmidgall-2025-agent-laboratory-using-llm/) - [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://md.research.elamur.ai/free/en/papers/tang-2024-medagents-large-language-models-as/) - [Executable Code Actions Elicit Better LLM Agents](https://md.research.elamur.ai/free/en/papers/wang-2024-executable-code-actions-elicit-better/) - [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://md.research.elamur.ai/free/en/papers/wu-2023-autogen-enabling-next-gen-llm/) - [The Rise and Potential of Large Language Model Based Agents: A Survey](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/) - [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://md.research.elamur.ai/free/en/papers/xiao-2024-infllm-training-free-long-context/) - [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://md.research.elamur.ai/free/en/papers/yang-2024-swe-agent-agent-computer-interfaces/) - [A Survey of Large Language Models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{wang2023survey, title = {{A Survey on Large Language Model based Autonomous Agents}}, author = {Wang, Lei and Ma, Chen and Feng, Xueyang and Zhang, Zeyu and Yang, Hao and Zhang, Jingsen and Chen, Zhiyuan and Tang, Jiakai and Chen, Xu and Lin, Yankai and Zhao, Wayne Xin and Wei, Zhewei and Wen, Ji-Rong}, year = {2023}, doi = {10.1007/s11704-024-40231-1}, eprint = {2308.11432}, archivePrefix = {arXiv}, url = {https://doi.org/10.1007/s11704-024-40231-1} } ``` - [← previous A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://md.research.elamur.ai/free/en/papers/yao-2023-survey-large-language-model-llm/) - [next → A Survey on Multimodal Large Language Models](https://md.research.elamur.ai/free/en/papers/yin-2023-survey-multimodal-large-language-models/) - [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/) ## References 11 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. 1. Mnih V, Kavukcuoglu K, Silver D, Rusu A A, Veness J, Bellemare M G, Graves A, Riedmiller M, Fidjeland A K, Ostrovski G, others . Human-level control through deep reinforcement learning. nature, 2015, 518(7540): 529–533 2. Lillicrap T P, Hunt J J, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wie… [find](https://scholar.google.com/scholar?q=1%2E+Mnih+V%2C+Kavukcuoglu+K%2C+Silver+D%2C+Rusu+A+A%2C+Veness+J%2C+Bellemare+M+G%2C+Graves+A%2C+Riedmiller+M%2C+Fidjeland+A+K%2C+Ostrovski+G%2C+others+%2E+Human%2Dlevel+control+through+deep+reinforcement+learning%2E+nature%2C+201) 2. Political Analysis, 2023, 31(3): 337–351 Fischer K A. Reflective linguistic programming (rlp): A stepping stone in socially-aware agi (socialagi). arXiv preprint arXiv:2305.12647, 2023 Rana K, Haviland J, Garg S, Abou-Chakra J, Reid I, Suenderhauf N. Sayplan: Grounding large language models using 3d… [find](https://scholar.google.com/scholar?q=Political+Analysis%2C+2023%2C+31%283%29%3A+337%E2%80%93351+Fischer+K+A%2E+Reflective+linguistic+programming+%28rlp%29%3A+A+stepping+stone+in+socially%2Daware+agi+%28socialagi%29%2E+arXiv+preprint+arXiv%3A2305%2E12647%2C+2023+Rana+K%2C+Havilan) [our card](https://md.research.elamur.ai/free/en/papers/wang-2023-describe-explain-plan-select-interactive/) 3. A generative agent with fast and slow thinking for complex interactive tasks. Advances in Neural Information Processing Systems, 2024, 36 Evans J S B, Stanovich K E. Dual-process theories of higher cognition: Advancing the debate. Perspectives on psychological science, 2013, 8(3): 223–241 Wang X, We… [find](https://scholar.google.com/scholar?q=A+generative+agent+with+fast+and+slow+thinking+for+complex+interactive+tasks%2E+Advances+in+Neural+Information+Processing+Systems%2C+2024%2C+36+Evans+J+S+B%2C+Stanovich+K+E%2E+Dual%2Dprocess+theories+of+higher+co) [our card](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/) 4. Intelligent Computing, 2024, 3: 0063 Karpas E, Abend O, Belinkov Y, Lenz B, Lieber O, Ratner N, Shoham Y, Bata H, Levine Y, Leyton-Brown K, others . Mrkl systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning. arXiv prep… [find](https://scholar.google.com/scholar?q=Intelligent+Computing%2C+2024%2C+3%3A+0063+Karpas+E%2C+Abend+O%2C+Belinkov+Y%2C+Lenz+B%2C+Lieber+O%2C+Ratner+N%2C+Shoham+Y%2C+Bata+H%2C+Levine+Y%2C+Leyton%2DBrown+K%2C+others+%2E+Mrkl+systems%3A+A+modular%2C+neuro%2Dsymbolic+architectur) [our card](https://md.research.elamur.ai/free/en/papers/suris-2023-vipergpt-visual-inference-python-execution/) 5. Science, 2023, 380(6650): 1108–1109 Zhou X, Li G, Liu Z. Llm as dba. arXiv preprint arXiv:2308.05481, 2023 He Z, Wu H, Zhang X, Yao X, Zheng S, Zheng H, Yu B. Chateda: A large language model powered autonomous agent for eda. In: 2023 ACM/IEEE 5th Workshop on Machine Learning for CAD (MLCAD). 2023, 1… [find](https://scholar.google.com/scholar?q=Science%2C+2023%2C+380%286650%29%3A+1108%E2%80%931109+Zhou+X%2C+Li+G%2C+Liu+Z%2E+Llm+as+dba%2E+arXiv+preprint+arXiv%3A2308%2E05481%2C+2023+He+Z%2C+Wu+H%2C+Zhang+X%2C+Yao+X%2C+Zheng+S%2C+Zheng+H%2C+Yu+B%2E+Chateda%3A+A+large+language+model+powered+a) 6. Computational Linguistics, 2024, 1–58 Li C, Wang J, Zhu K, Zhang Y, Hou W, Lian J, Xie X. Emotionprompt: Leveraging psychology for large language models enhancement via emotional stimulus. arXiv e-prints, 2023, arXiv–2307 Zhuo T Y, Li Z, Huang Y, Shiri F, Wang W, Haffari G, Li Y F. On robustness of… [find](https://scholar.google.com/scholar?q=Computational+Linguistics%2C+2024%2C+1%E2%80%9358+Li+C%2C+Wang+J%2C+Zhu+K%2C+Zhang+Y%2C+Hou+W%2C+Lian+J%2C+Xie+X%2E+Emotionprompt%3A+Leveraging+psychology+for+large+language+models+enhancement+via+emotional+stimulus%2E+arXiv+e%2Dpri) 7. ACM Computing Surveys, 2023, 55(12): 1–38 [find](https://scholar.google.com/scholar?q=ACM+Computing+Surveys%2C+2023%2C+55%2812%29%3A+1%E2%80%9338) 8. Jingsen Zhang is currently studying for a Ph.D. degree at Renmin University of China, Beijing, China. His research interests include recommender system. Lei Wang is a Ph.D. candidate at Renmin University of China, Beijing. His research focuses on recommender systems and agent-based large language mo… [find](https://scholar.google.com/scholar?q=Jingsen+Zhang+is+currently+studying+for+a+Ph%2ED%2E+degree+at+Renmin+University+of+China%2C+Beijing%2C+China%2E+His+research+interests+include+recommender+system%2E+Lei+Wang+is+a+Ph%2ED%2E+candidate+at+Renmin+Univers) 9. Yankai Lin received his B.E. and Zhewei Wei received his Ph.D. of Ph.D. degrees from Tsinghua Uni-Computer Science and Engineer-versity in 2014 and 2019. [find](https://scholar.google.com/scholar?q=Yankai+Lin+received+his+B%2EE%2E+and+Zhewei+Wei+received+his+Ph%2ED%2E+of+Ph%2ED%2E+degrees+from+Tsinghua+Uni%2DComputer+Science+and+Engineer%2Dversity+in+2014+and+2019%2E) 10. Af-ing from Hong Kong University of ter that, he worked as a senior re-Science and Technology. He did searcher in Tencent WeChat, and postdoctoral research in Aarhus joined Renmin University of China University from 2012 to 2014, and in 2022 as a tenure-track assistant professor. His main joined Ren… [find](https://scholar.google.com/scholar?q=Af%2Ding+from+Hong+Kong+University+of+ter+that%2C+he+worked+as+a+senior+re%2DScience+and+Technology%2E+He+did+searcher+in+Tencent+WeChat%2C+and+postdoctoral+research+in+Aarhus+joined+Renmin+University+of+China+) 11. Wayne Xin Zhao received his Ph.D. in Computer Science from Peking Ji-Rong Wen is a full professor, the University in 2014. His research executive dean of Gaoling School interests include data mining, natu-of Artificial Intelligence, and the ral language processing and infor-dean of School of Informa… [find](https://scholar.google.com/scholar?q=Wayne+Xin+Zhao+received+his+Ph%2ED%2E+in+Computer+Science+from+Peking+Ji%2DRong+Wen+is+a+full+professor%2C+the+University+in+2014%2E+His+research+executive+dean+of+Gaoling+School+interests+include+data+mining%2C+)