{"id":13754213,"url":"https://github.com/lafmdp/Awesome-Papers-Autonomous-Agent","last_synced_at":"2025-05-09T22:31:28.598Z","repository":{"id":203481960,"uuid":"706764290","full_name":"lafmdp/Awesome-Papers-Autonomous-Agent","owner":"lafmdp","description":"A collection of recent papers on building autonomous agent. Two topics included: RL-based / LLM-based agents.","archived":false,"fork":false,"pushed_at":"2024-12-24T05:23:54.000Z","size":372,"stargazers_count":684,"open_issues_count":1,"forks_count":57,"subscribers_count":13,"default_branch":"main","last_synced_at":"2025-05-07T10:01:50.185Z","etag":null,"topics":["agent","artificial-intelligence","autonomous-agent","awesome-paper-collection","large-language-models","machine-learning","natural-language-processing","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lafmdp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-10-18T15:14:05.000Z","updated_at":"2025-05-05T03:19:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"f411bb53-5625-43bf-9221-6f5a590cc0e0","html_url":"https://github.com/lafmdp/Awesome-Papers-Autonomous-Agent","commit_stats":{"total_commits":10,"total_committers":2,"mean_commits":5.0,"dds":0.09999999999999998,"last_synced_commit":"746d1ccc1f550da2bac4ba2b1f32ca7245c4b750"},"previous_names":["lafmdp/awesome-papers-autonomous-agent"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lafmdp%2FAwesome-Papers-Autonomous-Agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lafmdp%2FAwesome-Papers-Autonomous-Agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lafmdp%2FAwesome-Papers-Autonomous-Agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lafmdp%2FAwesome-Papers-Autonomous-Agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lafmdp","download_url":"https://codeload.github.com/lafmdp/Awesome-Papers-Autonomous-Agent/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253335673,"owners_count":21892713,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","artificial-intelligence","autonomous-agent","awesome-paper-collection","large-language-models","machine-learning","natural-language-processing","reinforcement-learning"],"created_at":"2024-08-03T09:01:50.223Z","updated_at":"2025-05-09T22:31:28.588Z","avatar_url":"https://github.com/lafmdp.png","language":null,"funding_links":[],"categories":["Related","Agent","Other Lists","A01_文本生成_文本对话","Others"],"sub_categories":["Paper-List Repo","TeX Lists","大语言对话模型及数据"],"readme":"![](figs/agent-collection.png)\n\n# Awesome-Papers-Autonomous-Agent\n\nThis is a collection of recent papers focusing on autonomous agent. Here is how Wikipedia defines Agent:\n\n\u003e In artificial intelligence, an intelligent agent is an agent acting in an intelligent manner; It perceives its environment, takes actions autonomously in order to achieve goals, and may improve its performance with learning or acquiring knowledge. An intelligent agent may be simple or complex: A thermostator other control systemis considered an example of an intelligent agent, as is a human being, as is any system that meets the definition, such as a firm, a state, or a biome.\n\nThus, the key of an agent is that it can \u003ci\u003eachieve goals\u003c/i\u003e, \u003ci\u003eacquire knowledge\u003c/i\u003e and \u003ci\u003econtinually improve\u003c/i\u003e.\nThe traditional agents in RL research will not be considered in this collection.\nThough LLM-based agents have caught people's eyes in recent research, RL-based agents also take their special position.\nSpecifically, this repo is interested in two types of agent: RL-based agent and LLM-based agent. \n\nNote that this paper list is **under active maintaince**. Free free to open an issue if you found any missed papers that fit the topic.\n\n\n\n------\n\n## Update history\n\n- 2024/01/31: Add a special list for surveys on autonomous agent.\n- 2023/12/08: Add papers accepted by [ICML'23](https://icml.cc/virtual/2023/papers.html?filter=titles) and [ICLR'23]() :rocket:\n- 2023/11/08: Add papers accepted by [NeurIPS'23](https://openreview.net/group?id=NeurIPS.cc/2023/Conference\u0026referrer=%5BHomepage%5D(%2F)). Add related links (project page or github) to these accepted papers :tada:\n- 2023/10/25: Classify all papers based on their research topics. Check ToC for the standard of classification :clap:\n- 2023/10/18: Release first version of collection, including papers submitted to [ICLR 2024](https://openreview.net/group?id=ICLR.cc/2024/Conference) :rocket:\n\n\n\u003c!-- START doctoc generated TOC please keep comment here to allow auto update --\u003e\n\u003c!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE --\u003e\n**Table of Contents**\n\n- [Surveys](#surveys)\n- [RL-based agent](#rl-based-agent)\n  - [Instruction following](#instruction-following)\n  - [Build agent based on World model](#build-agent-based-on-world-model)\n  - [Language as knowledge](#language-as-knowledge)\n  - [LLM as a tool](#llm-as-a-tool)\n  - [Generalization across tasks](#generalization-across-tasks)\n  - [Continual learning](#continual-learning)\n  - [Combine RL and LLM](#combine-rl-and-llm)\n  - [Transformer-based policy](#transformer-based-policy)\n  - [Trajectory to language](#trajectory-to-language)\n  - [Trajectory predication](#trajectory-predication)\n  - [Others](#others)\n- [LLM-based agent](#llm-based-agent)\n  - [Multimodal](#multimodal)\n  - [Train LLM for generalization \u0026 adaptation](#train-llm-for-generalization--adaptation)\n  - [Task-specific designing](#task-specific-designing)\n  - [Multi-agent (e.g., society, coperation)](#multi-agent-eg-society-coperation)\n  - [Experimental analysis](#experimental-analysis)\n  - [Benchmark \u0026 Dataset](#benchmark--dataset)\n  - [Applications](#applications)\n  - [Algorithm design](#algorithm-design)\n  - [Combined with RL](#combined-with-rl)\n  - [Others](#others-1)\n\n\u003c!-- END doctoc generated TOC please keep comment here to allow auto update --\u003e\n\n\n------\n\n## Surveys\n- [A Survey on Large Language Model based Autonomous Agents](https://arxiv.org/pdf/2308.11432.pdf?trk=public_post_comment-text)\n- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://arxiv.org/pdf/2309.07864.pdf)\n\n\n## RL-based agent\n\n\n### Instruction following\n- [NeurIPS'23] [Natural Language-conditioned Reinforcement Learning with Inside-out Task Language Development and Translation](https://arxiv.org/abs/2302.09368)\n- [NeurIPS'23] [Guide Your Agent with Adaptive Multimodal Rewards](https://openreview.net/attachment?id=G8nal7MpIQ\u0026name=pdf) [[project](https://sites.google.com/view/2023arp)]\n- [Compositional Instruction Following with Language Models and Reinforcement Learning](https://openreview.net/forum?id=lIwp1C1eSK)\n- [RT-1: Robotics Transformer for Real-World Control at Scale](https://arxiv.org/abs/2212.06817) [[blog](https://blog.research.google/2022/12/rt-1-robotics-transformer-for-real.html)]\n- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://robotics-transformer2.github.io/assets/rt2.pdf) [[blog](https://deepmind.google/discover/blog/rt-2-new-model-translates-vision-and-language-into-action/)]\n- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://arxiv.org/abs/2310.08864) [[blog](https://deepmind.google/discover/blog/scaling-up-learning-across-many-different-robot-types/)]\n- [NeurIPS'23] [Guide Your Agent with Adaptive Multimodal Rewards](https://openreview.net/attachment?id=G8nal7MpIQ\u0026name=pdf) [[project](https://sites.google.com/view/2023arp)]\n- [LEO: An Embodied Generalist Agent in 3D World](https://arxiv.org/abs/2311.12871) [[project](https://embodied-generalist.github.io/)]\n\n\n### Build agent based on World model\n- [ICLR'23 Oral] [Transformers are Sample-Efficient World Models](https://openreview.net/forum?id=vhFu1Acb0xb) [[code](https://github.com/eloialonso/iris)]\n- [Learning to Model the World with Language](https://openreview.net/forum?id=eWLOoaShEH)\n- [MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning](https://openreview.net/forum?id=1RE0H6mU7M)\n\n\n### Language as knowledge \n- [Learning with Language Inference and Tips for Continual Reinforcement Learning](https://openreview.net/forum?id=zEhTnQZB3D)\n- [Informing Reinforcement Learning Agents by Grounding Natural Language to Markov Decision Processes](https://openreview.net/forum?id=P4op21eju0)\n- [Language Reward Modulation for Pretraining Reinforcement Learning](https://openreview.net/forum?id=SWRFC2EupO)\n\n\n### LLM as a tool\n\n- [NeurIPS'23] [Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents](https://openreview.net/forum?id=Ny3GcHLyzj)\n- [ICLR'23] [Reward Design with Language Models](https://openreview.net/forum?id=10uNUgI5Kl) [[code](https://github.com/minaek/reward_design_with_llms)]\n- [ICML'23] [RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents](https://icml.cc/virtual/2023/poster/24583) [[Poster](https://icml.cc/media/PosterPDFs/ICML%202023/24583.png?t=1688077847.801905)]\n- [ICML'23] [Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling](https://icml.cc/virtual/2023/poster/24286) [[Project](https://deckardagent.github.io/)][[Code](https://github.com/DeckardAgent/deckard)]\n- [ICML'23] [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://icml.cc/virtual/2023/poster/23938)\n- [Leveraging Large Language Models for Optimised Coordination in Textual Multi-Agent Reinforcement Learning](https://openreview.net/forum?id=1PPjf4wife)\n- [Text2Reward: Dense Reward Generation with Language Models for Reinforcement Learning](https://openreview.net/forum?id=tUM39YTRxH)\n- [Language to Rewards for Robotic Skill Synthesis](https://language-to-reward.github.io )\n- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://eureka-research.github.io)\n- [STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models](https://openreview.net/forum?id=LXiG2WqKXR)\n\n\n### Generalization across tasks\n- [A Generalist Agent](https://arxiv.org/abs/2205.06175)\n- [AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents](https://openreview.net/forum?id=M6XWoEdmwf)\n\n\n### Continual learning\n- [ADAPTER-RL: Adaptation of Any Agent using Reinforcement Learning](https://openreview.net/forum?id=LVp217SAtb)\n- [Online Continual Learning for Interactive Instruction Following Agents](https://openreview.net/forum?id=7M0EzjugaN)\n- [NeurIPS'23] [A Definition of Continual Reinforcement Learning](https://openreview.net/attachment?id=ZZS9WEWYbD\u0026name=pdf)\n\n### Combine RL and LLM\n- [NeurIPS'23] [Large Language Models Are Semi-Parametric Reinforcement Learning Agents](https://openreview.net/forum?id=ZcJa1R6j3v)\n- [RoboGPT : An intelligent agent of making embodied long-term decisions for daily instruction tasks](https://openreview.net/forum?id=x4fm4T2tjM)\n- [Can Language Agents Approach the Performance of RL? An Empirical Study On OpenAI Gym](https://openreview.net/forum?id=F0q880yOgY)\n- [RLAdapter: Bridging Large Language Models to Reinforcement Learning in Open Worlds](https://openreview.net/forum?id=3s4fZTr1ce)\n\n\n### Transformer-based policy\n- [NeurIPS'23] [Cross-Episodic Curriculum for Transformer Agents](https://openreview.net/forum?id=afKnrwJBAl). [[project](https://cec-agent.github.io/)]\n\n\n### Trajectory to language\n- [NeurIPS'23] [State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding](https://openreview.net/attachment?id=xGz0wAIJrS\u0026name=pdf)\n- [NeurIPS'23] [Semantic HELM: A Human-Readable Memory for Reinforcement Learning](https://openreview.net/pdf?id=ebMPmx5mr7)\n- [ICML'23] [Distilling Internet-Scale Vision-Language Models into Embodied Agents](https://icml.cc/virtual/2023/poster/24664)\n- [Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation](https://openreview.net/forum?id=PKsTHJXn4d)\n\n\n### Trajectory predication\n- [Multi-agent Trajectory Prediction with Scalable Diffusion Transformer](https://openreview.net/forum?id=crP1HxQ5iw)\n\n\n### Others\n- [Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain](https://openreview.net/forum?id=BqEvdOS1Hs)\n- [A Competition Winning Deep Reinforcement Learning Agent in microRTS](https://openreview.net/forum?id=6ssOs9BBxa)\n- [Aligning Agents like Large Language Models](https://openreview.net/forum?id=kQqZVayz07)\n\n\n------\n\n## LLM-based agent\n\n### Multimodal\n\n- [ICML'23] [PaLM-E: An Embodied Multimodal Language Model](https://icml.cc/virtual/2023/poster/23969)\n- [Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds](https://openreview.net/forum?id=NltzxpG0nz)\n- [Multimodal Web Navigation with Instruction-Finetuned Foundation Models](https://openreview.net/forum?id=efFmBWioSc)\n- [You Only Look at Screens: Multimodal Chain-of-Action Agents](https://openreview.net/forum?id=iSAgvYhZzg)\n- [Learning Embodied Vision-Language Programming From Instruction, Exploration, and Environmental Feedback](https://openreview.net/forum?id=VUA9LSmC2r)\n- [An Embodied Generalist Agent in 3D World](https://openreview.net/forum?id=4QaKdsh15T)\n- [JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models](https://arxiv.org/abs/2311.05997)\n\n\n\n### Train LLM for generalization \u0026 adaptation\n\n- [FireAct: Toward Language Agent Finetuning](https://openreview.net/forum?id=RqUMWdDg52)\n- [Adapting LLM Agents Through Communication](https://openreview.net/forum?id=wOelVq8fwL)\n- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://openreview.net/forum?id=OqlmgmS4Wr)\n- [Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization](https://openreview.net/forum?id=KOZu91CzbK)\n\n\n### Task-specific designing\n\n- [NeurIPS'23] [Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents](https://openreview.net/forum?id=KtvPdGb31Z)\n- [NeurIPS'23] [SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks](https://openreview.net/forum?id=Rzk3GP1HN7) [[Github](https://github.com/yuchenlin/SwiftSage)]\n- [Rethinking the Buyer’s Inspection Paradox in Information Markets with Language Agents](https://openreview.net/forum?id=6werMQy1uz)\n- [A Language-Agent Approach to Formal Theorem-Proving](https://openreview.net/forum?id=XCMbagV0No)\n- [Agent Instructs Large Language Models to be General Zero-Shot Reasoners](https://openreview.net/forum?id=zIJFG7wW2d)\n- [Ghost in the Minecraft: Hierarchical Agents for Minecraft via Large Language Models with Text-based Knowledge and Memory](https://openreview.net/forum?id=cTOL99p5HL)\n- [PaperQA: Retrieval-Augmented Generative Agent for Scientific Research](https://openreview.net/forum?id=clU5xWyItb)\n- [Language Agents for Detecting Implicit Stereotypes in Text-to-image Models at Scale](https://openreview.net/forum?id=XW0gD13oQp)\n- [Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4](https://arxiv.org/abs/2309.17277)\n\n### Multi-agent (e.g., society, coperation)\n- [CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving](https://arxiv.org/abs/2404.17729)\n- [Building Cooperative Embodied Agents Modularly with Large Language Models](https://openreview.net/forum?id=EnXJfQqy0K)\n- [OKR-Agent: An Object and Key Results Driven Agent System with Hierarchical Self-Collaboration and Self-Evaluation](https://openreview.net/forum?id=Mngdhgi711)\n- [MetaGPT: Meta Programming for Multi-Agent Collaborative Framework](https://openreview.net/forum?id=VtmBAGCN7o)\n- [AutoAgents: A Framework for Automatic Agent Generation](https://openreview.net/forum?id=PhJUd3mbhP)\n- [Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization](https://openreview.net/forum?id=i43XCU54Br)\n- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://openreview.net/forum?id=EHg5GDnyq1)\n- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://openreview.net/forum?id=ueqTjOcuLc)\n- [REX: Rapid Exploration and eXploitation for AI agents](https://openreview.net/forum?id=8TAGx549Ns)\n- [Emergence of Social Norms in Large Language Model-based Agent Societies](https://arxiv.org/abs/2403.08251)\n\n\n### Experimental analysis\n\n- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://openreview.net/forum?id=GEcwtMk1uA)\n- [Evaluating Multi-Agent Coordination Abilities in Large Language Models](https://openreview.net/forum?id=OEDM8mzbsl)\n- [Large Language Models as Gaming Agents](https://openreview.net/forum?id=iS3fQooCaa)\n- [Benchmarking Large Language Models as AI Research Agents](https://openreview.net/forum?id=N9wD4RFWY0)\n- [Adaptive Environmental Modeling for Task-Oriented Language Agents](https://openreview.net/forum?id=H0RztJssmQ)\n- [CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization](https://openreview.net/forum?id=d5DGVHMdsC)\n\n### Benchmark \u0026 Dataset\n- [ACL'24] [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://arxiv.org/abs/2407.18901) [[website](https://appworld.dev/)][[blog](https://appworld.dev/blog)]\n- [ICLR'23] [Task Ambiguity in Humans and Language Models](https://openreview.net/forum?id=QrnDe_9ZFd8) [[code](https://github.com/kunhanda/task_ambiguity)]\n- [SmartPlay : A Benchmark for LLMs as Intelligent Agents](https://openreview.net/forum?id=S2oTVrlcp3)\n- [AgentBench: Evaluating LLMs as Agents](https://openreview.net/forum?id=zAdUB0aCTQ)\n- [Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena](https://openreview.net/forum?id=crMMk4I8Wy)\n- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://openreview.net/forum?id=mM7VurbA4r)\n- [SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series](https://openreview.net/forum?id=s9z0HzWJJp)\n- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://openreview.net/forum?id=oKn9c6ytLx)\n- [LLM-Deliberation: Evaluating LLMs with Interactive Multi-Agent Negotiation Game](https://openreview.net/forum?id=cfL8zApofK)\n- [Evaluating Large Language Models at Evaluating Instruction Following](https://openreview.net/forum?id=tr0KidwPLc)\n- [CivRealm: A Learning and Reasoning Odyssey for Decision-Making Agents](https://openreview.net/forum?id=UBVNwD3hPN)\n\n### Applications\n\n- [Lyfe Agents: generative agents for low-cost real-time social interactions](https://openreview.net/forum?id=VaZa8zj0Yw)\n- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://openreview.net/forum?id=tEAF9LBdgu)\n\n\n### Algorithm design\n- [ICLR'23 Oral] [ReAct: Synergizing Reasoning and Acting in Language Models](https://openreview.net/forum?id=WE_vluYUL-X) [[code](https://www.catalyzex.com/paper/arxiv:2210.03629/code)]\n- [NeurIPS'23] [AdaPlanner: Adaptive Planning from Feedback with Language Models](https://openreview.net/forum?id=rnKgbKmelt) [[github](https://github.com/haotiansun14/AdaPlanner)]\n- [Prospector: Improving LLM Agents with Self-Asking and Trajectory Ranking](https://openreview.net/forum?id=YKK1jXEWja)\n- [Formally Specifying the High-Level Behavior of LLM-Based Agents](https://openreview.net/forum?id=FRxDrdysBt)\n- [Cumulative Reasoning With Large Language Models](https://arxiv.org/pdf/2308.04371.pdf)\n\n\n### Combined with RL\n- [NeurIPS'23] [Reflexion: language agents with verbal reinforcement learning](https://openreview.net/forum?id=vAElhFcKW6) [[code](https://github.com/noahshinn024/reflexion)]\n- [Teaching LLMs to Teach Themselves Better Instructions via Reinforcement Learning](https://openreview.net/forum?id=wlRp8IdLkN)\n- [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://openreview.net/forum?id=N1gmpVd4iE)\n\n### Others\n- [NeurIPS'24] [Can Graph Learning Improve Planning in LLM-based Agents?](https://arxiv.org/abs/2405.19119) [[code](https://github.com/WxxShirley/GNN4TaskPlan)] [[chinese blog](https://zhuanlan.zhihu.com/p/936340518)] [[english blog](https://medium.com/@xxwu1120/llms-still-cant-plan-can-graph-learning-improve-it-15b7806288be)]\n- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://arxiv.org/abs/2410.06153)[[Project page](https://tsinghua-fib-lab.github.io/AgentSquare_website/)][[Github](https://github.com/tsinghua-fib-lab/AgentSquare)]\n- [LUMOS: Towards Language Agents that are Unified, Modular, and Open Source](https://openreview.net/forum?id=VmnWoLbzCS)\n- [Lemur: Harmonizing Natural Language and Code for Language Agents](https://openreview.net/forum?id=hNhwSmtXRh)\n- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://openreview.net/forum?id=6LNTSrJjBe)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flafmdp%2FAwesome-Papers-Autonomous-Agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flafmdp%2FAwesome-Papers-Autonomous-Agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flafmdp%2FAwesome-Papers-Autonomous-Agent/lists"}