A Survey on LLM-based Autonomous Agents

Growth Trend

Autonomous agents are designed to achieve specific objectives through self-guided instructions. With the emergence and growth of large language models (LLMs), there is a growing trend in utilizing LLMs as fundamental controllers for these autonomous agents. While previous studies in this field have achieved remarkable successes, they remain independent proposals with little effort devoted to a systematic analysis. To bridge this gap, we conduct a comprehensive survey study, focusing on the construction, application, and evaluation of LLM-based autonomous agents. In particular, we first explore the essential components of an AI agent, including a profile module, a memory module, a planning module, and an action module. We further investigate the application of LLM-based autonomous agents in the domains of natural sciences, social sciences, and engineering. Subsequently, we delve into a discussion of the evaluation strategies employed in this field, encompassing both subjective and objective methods. Our survey aims to serve as a resource for researchers and practitioners, providing insights, related references, and continuous updates on this exciting and rapidly evolving field.

To our knowledge, this is the first systematic survey paper in the field of LLM-based autonomous agents.

Paper link: A Survey on Large Language Model based Autonomous Agents

Update Records

  • ๐Ÿ”ฅ [9/8/2023] The second version of our survey has been released on arXiv.

    Updated contents
    • ๐Ÿ“š Additional References

      • We have added 31 new works until 9/1/2023 to make the survey more comprehensive and up-to-date.
    • ๐Ÿ“Š New Figures

      • Figure 3: This is a new figure illustrating the differences and similarities between various planning approaches. This helps in gaining a clearer understanding of the comparisons between different planning methods. single-path and multi-path reasoning
      • Figure 4: This is a new figure that describes the evolutionary path of model capability acquisition from the "Machine Learning era" to the "Large Language Model era" and then to the "Agent era." Specifically, a new concept, "mechanism engineering," has been introduced, which, along with "parameter learning" and "prompt engineering," forms part of this evolutionary path. Capabilities Acquisition
    • ๐Ÿ” Optimized Classification System

      • We have slightly modified the classification system in our survey to make it more logical and organized.
  • ๐Ÿ”ฅ [8/23/2023] The first version of our survey has been released on arXiv.

Table of Content

๐Ÿค– Construction of LLM-based Autonomous Agent

Architecture Design

Model Profile Memory Planning Action CA Paper Code
Operation Structure
WebGPT - - - - w/ tools w/ fine-tuning Paper -
SayCan - - - w/o feedback w/o tools w/o fine-tuning Paper Code
MRKL - - - w/o feedback w/ tools - Paper -
Inner Monologue - - - w/ feedback w/o tools w/o fine-tuning Paper Code
Social Simulacra GPT-Generated - - - w/o tools - Paper -
ReAct - - - w/ feedback w/ tools w/ fine-tuning Paper Code
MALLM - Read/Write Hybrid - w/o tools - Paper -
DEPS - - - w/ feedback w/o tools w/o fine-tuning Paper Code
Toolformer - - - w/o feedback w/ tools w/ fine-tuning Paper Code
Reflexion - Read/Write/
Reflection
Hybrid w/ feedback w/o tools w/o fine-tuning Paper Code
CAMEL Handcrafting & GPT-Generated - - w/ feedback w/o tools - Paper Code
API-Bank - - - w/ feedback w/ tools w/o fine-tuning Paper Code
ViperGPT - - - - w/ tools - Paper Code
HuggingGPT - - Unified w/o feedback w/ tools - Paper Code
Generative Agents Handcrafting Read/Write/
Reflection
Hybrid w/ feedback w/o tools - Paper Code
LLM+P - - - w/o feedback w/o tools - Paper -
ChemCrow - - - w/ feedback w/ tools - Paper Code
OpenAGI - - - w/ feedback w/ tools w/ fine-tuning Paper Code
AutoGPT - Read/Write Hybrid w/ feedback w/ tools w/o fine-tuning - Code
SCM - Read/Write Hybrid - w/o tools - Paper Code
Socially Alignment - Read/Write Hybrid - w/o tools Example Paper Code
GITM - Read/Write/
Reflection
Hybrid w/ feedback w/o tools w/ fine-tuning Paper Code
Voyager - Read/Write/
Reflection
Hybrid w/ feedback w/o tools w/o fine-tuning Paper Code
Introspective Tips - - - w/ feedback w/o tools w/o fine-tuning Paper -
RET-LLM - Read/Write Hybrid - w/o tools w/ fine-tuning Paper -
ChatDB - Read/Write Hybrid w/ feedback w/ tools - Paper -
S3 Dataset alignment Read/Write/
Reflection
Hybrid - w/o tools w/ fine-tuning Paper -
ChatDev Handcrafting Read/Write/
Reflection
Hybrid w/ feedback w/o tools w/o fine-tuning Paper Code
ToolLLM - - - w/ feedback w/ tools w/ fine-tuning Paper Code
MemoryBank - Read/Write/
Reflection
Hybrid - w/o tools - Paper Code
MetaGPT Handcrafting Read/Write/
Reflection
Hybrid w/ feedback w/ tools - Paper Code

๐Ÿ“ Applications of LLM-based Autonomous Agent

Title Social Science Natural Science Engineering Paper Code
Drori et al. - Science Education - Paper -
SayCan - - Robotics & Embodied AI Paper Code
Inner monologue - - Robotics & Embodied AI Paper Code
Language-Planners - - Robotics & Embodied AI Paper Code
Social Simulacra Social Simulation - - Paper -
TE Psychology - - Paper Code
Out of One Political Science and Economy - - Paper -
LIBRO CS&SE - - Paper -
Blind Judgement Jurisprudence - - Paper -
Horton Political Science and Economy - - Paper -
DECKARD - - Robotics & Embodied AI Paper Code
Planner-Actor-Reporter - - Robotics & Embodied AI Paper -
DEPS - - Robotics & Embodied AI Paper -
RCI - - CS&SE Paper Code
Generative Agents Social Simulation - - Paper Code
SCG - - CS&SE Paper -
IGLU - - Civil Engineering Paper -
IELLM - - Industrial Automation Paper -
ChemCrow - Document and Data Management;
Documentation, Data Managent;
Science Education
- Paper -
Boiko et al. - Document and Data Management;
Documentation, Data Managent;
Science Education
- Paper -
GPT4IA - - Industrial Automation Paper Code
Self-collaboration - - CS&SE Paper -
E2WM - - Robotics & Embodied AI Paper Code
Akata et al. Psychology - - Paper -
Ziems et al. Psychology;
Political Science and Economy;
Research Assistant
- - Paper -
AgentVerse Social Simulation - - Paper Code
SmolModels - - CS&SE - Code
TidyBot - - Robotics & Embodied AI Paper Code
PET - - Robotics & Embodied AI Paper -
Voyager - - Robotics & Embodied AI Paper Code
GITM - - Robotics & Embodied AI Paper Code
NLSOM - Science Education - Paper -
LLM4RL - - Robotics & Embodied AI Paper -
GPT Engineer - - CS&SE - Code
Grossman et al. - Experiment Assistant;
Science Education
- Paper -
SQL-PALM - - CS&SE Paper -
REMEMBER - - Robotics & Embodied AI Paper -
DemoGPT - - CS&SE - Code
Chatlaw Jurisprudence - - Paper Code
RestGPT - - CS&SE Paper Code
Dialogue shaping - - Robotics & Embodied AI Paper -
TaPA - - Robotics & Embodied AI Paper -
Ma et al. Psychology - - Paper -
Math Agents - Science Education - Paper -
SocialAI School Social Simulation - - Paper -
Unified Agent - - Robotics & Embodied AI Paper -
Wiliams et al. Social Simulation - - Paper -
Li et al. Social Simulation - - Paper -
S3 Social Simulation - - Paper -
Dialogue Shaping - - Robotics & Embodied AI Paper -
RoCo - - Robotics & Embodied AI Paper Code
Sayplan - - Robotics & Embodied AI Paper Code
ToolLLM - - CS&SE Paper Code
ChatDEV - - CS&SE Paper -
Chao et al. Social Simulation - - Paper -
AgentSims Social Simulation - - Paper Code
ChatMOF - Document and Data Management;
Science Education
- Paper -
MetaGPT - - CS&SE Paper Code
Codehelp - Science Education CS&SE Paper -
AutoGen - Science Education - Paper -
RAH - - CS&SE Paper -
DB-GPT - - CS&SE Paper Code
RecMind - - CS&SE Paper -
ChatEDA - - CS&SE Paper -
InteRecAgent - - CS&SE Paper -
PentestGPT - - CS&SE Paper -
Codehelp - - CS&SE Paper -
ProAgent - - Robotics & Embodied AI Paper -

๐Ÿ“Š Evaluation on LLM-based Autonomous Agent

Model Subjective Objective Benchmark Paper Code
WebShop - Environment Simulation;
Multi-task Evaluation
โœ“ Paper Code
Social Simulacra Human Annotation Social Evaluation - Paper -
TE - Social Evaluation - Paper Code
LIBRO - Software Testing - Paper -
ReAct - Environment Simulation โœ“ Paper Code
Out of One, Many Turing Test Social Evaluation;
Multi-task Evaluation
- Paper -
DEPS - Environment Simulation โœ“ Paper -
Jalil et al. - Software Testing - Paper Code
Reflexion - Environment Simulation;
Multi-task Evaluation
- Paper Code
IGLU - Environment Simulation โœ“ Paper -
Generative Agents Human Annoation;
Turing Test
- - Paper Code
ToolBench Human Annoation Multi-task Evalution โœ“ Paper Code
GITM - Environment Simulation โœ“ Paper Code
Two-Failures - Multi-task Evalution - Paper -
Voyager - Environment Simulation โœ“ Paper Code
SocKET - Social Evaluation;
Multi-task Evaluation
โœ“ Paper -
Mobile-Env - Environment Simulation;
Multi-task Evaluation
โœ“ Paper Code
Clembench - Environment Simulation;
Multi-task Evaluation
โœ“ Paper Code
Dialop - Social Evaluation โœ“ Paper Code
Feldt et al. - Software Testing - Paper -
CO-LLM Human Annoation Environment Simulation - Paper Code
Tachikuma Human Annoation Environment Simulation โœ“ Paper -
WebArena - Environment Simulation โœ“ Paper Code
RocoBench - Environment Simulation;
Social Evaluation;
Multi-task Evaluation
โœ“ Paper Code
AgentSims - Social Evaluation - Paper Code
AgentBench - Multi-task Evaluation โœ“ Paper Code
BOLAA - Environment Simulation;
Multi-task Evaluation;
Software Testing
โœ“ Paper Code
Gentopia - Isolated Reasoning;
Multi-task Evaluation
โœ“ Paper Code
EmotionBench Human Annotation - โœ“ Paper Code
PTB - Software Testing โœ“ Paper -

๐ŸŒ More Comprehensive Summarization

We are maintaining an interactive table that contains more comprehensive papers related to LLM-based Agents. This table includes details such as tags, authors, publication date, and more, allowing you to sort, filter, and find the papers of interest to you. Complete Table

๐Ÿ‘จโ€๐Ÿ‘จโ€๐Ÿ‘งโ€๐Ÿ‘ฆ Maintainers

๐Ÿ“š Citation

If you find this survey useful, please cite our paper:

@misc{wang2023survey,
      title={A Survey on Large Language Model based Autonomous Agents}, 
      author={Lei Wang and Chen Ma and Xueyang Feng and Zeyu Zhang and Hao Yang and Jingsen Zhang and Zhiyuan Chen and Jiakai Tang and Xu Chen and Yankai Lin and Wayne Xin Zhao and Zhewei Wei and Ji-Rong Wen},
      year={2023},
      eprint={2308.11432},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}

๐Ÿ’ช How to Contribute

If you have a paper or are aware of relevant research that should be incorporated, please contribute via pull requests, issues, email, or other suitable methods.

๐Ÿซก Acknowledgement

We thank the following people for their valuable suggestions and contributions to this survey:

๐Ÿ“ง Contact Us

If you have any questions or suggestions, please contact us via: