This is the reading list for the survey "A Survey of LLM-based Agents Optimization" (Paper Link), which systematically explores various optimization techniques for enhancing LLM-based agents. The survey categorizes existing works into parameter-driven optimization, parameter-free optimization, datasets and benchmarks, and real-world applications. We will keep adding papers and improving the list. Any suggestions and PRs are welcome!

• FireAct : TOWARD LANGUAGE AGENT FINE-TUNING (arXiv 2023) [paper] [code]
• AgentTuning: Enabling Generalized Agent Abilities for LLMs (ACL-findings 2024) [paper] [code]
• SMART: Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks (arXiv 2024) [paper] [code]
• Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models (ACL-findings 2024) [paper] [code]
• Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk (arXiv 2024) [paper]
• SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales (EMNLP 2024) [paper] [code]
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments (arXiv 2024) [paper] [code]
• Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents (ACL 2024) [paper] [code]
• Agent LUMOS: Unified and Modular Training for Open-Source Language Agents (ACL 2024) [paper] [code]
• LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error (ACL 2024) [paper] [code]
• NAT: Learning From Failure: Integrating Negative Examples when Fine-tuning LLMs as Agents (arXiv 2024) [paper] [code]
• OPTIMA: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System (arXiv 2024) [paper] [code]
• Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning (NAACL 2024) [paper] [code]
• AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning (arXiv 2024) [paper] [code]
• TORA: A TOOL-INTEGRATED REASONING AGENT FOR MATHEMATICAL PROBLEM SOLVING (ICLR 2024) [paper] [code]
• ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent (arxiv 2023) [paper]
• AGENTBANK: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories (ACL-Findings 2024) [paper] [code]
• ADASWITCH: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning (EMNLP 2024) [paper]
• Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement (EMNLP 2024) [paper] [code]
• Re-ReST: Reflection-Reinforced Self-Training for Language Agents (EMNLP 2024) [paper] [code]
• Retrospex: Language Agent Meets Offline Reinforcement Learning Critic (EMNLP 2024) [paper] [code]
• ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator (EMNLP 2024) [paper] [code]
• SWIFTSAGE: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks (NeurIPS 2023) [paper] [code]
• NLRL: Natural Language Reinforcement Learning (arXiv 2024) [paper] [code]
• AGILE: A Novel Reinforcement Learning Framework of LLM Agents (NeurIPS 2024) [paper] [code]
• COEVOL: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation (arXiv 2024) [paper] [code]
• E2CL: Exploration-based Error Correction Learning for Embodied Agents (EMNLP-Findings 2024) [paper][code]
• STeCa: Step-level Trajectory Calibration for LLM Agent Learning (arXiv 2025) [paper][code]
• Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning (NeurIPS 2024) [paper] [code]
• ATLaS: Agent Tuning via Learning Critical Steps (ACL 2025) [paper]
• Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies (arXiv 2025) [paper]
• Agent Planning with World Knowledge Model (NeurIPS 2024) [paper] [code]
• MULTIAGENT FINETUNING: SELF IMPROVEMENT WITH DIVERSE REASONING CHAINS (ICLR 2025) [paper] [code]
• Disentangling Reasoning Tokens and Boilerplate Tokens For Language Model Fine-tuning (ACL 2025) [paper]
• Rearchitecting LLMs (Manning Publications 2025) [book]

• CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models (arXiv 2024) [paper] [code]
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning (arXiv 2024) [paper]
• WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning (arXiv 2024) [paper] [code]
• SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales (EMNLP 2024) [paper] [code]
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments (arXiv 2024) [paper] [code]
• Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning (arXiv 2024) [paper]
• GELI: Global Reward to Local Rewards: Multimodal-Guided Decomposition for Improving Dialogue Agents (EMNLP 2024) [paper]
• AGILE: A Novel Reinforcement Learning Framework of LLM Agents (NeurIPS 2024) [paper] [code]
• Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents (arxiv) [paper]
• DMPO: Direct Multi-Turn Preference Optimization for Language Agents (EMNLP 2024) [paper] [code]
• Re-ReST: Reflection-Reinforced Self-Training for Language Agents (EMNLP 2024) [paper] [code]
• ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator (EMNLP 2024) [paper] [code]
• OPTIMA: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System (arXiv 2024) [paper] [code]
• EPO: Hierarchical LLM Agents with Environment Preference Optimization (EMNLP 2024) [paper] [code]
• Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement (EMNLP 2024) [paper] [code]
• AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback (NeurIPS 2024) [paper] [code]
• SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks (arXiv 2025) [paper] [code]
• Reinforcing Language Agents via Policy Optimization with Action Decomposition (NeurIPS 2024) [paper] [code]
• STeCa: Step-level Trajectory Calibration for LLM Agent Learning (arXiv 2025) [paper][code]
• DITS: Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search (arXiv 2025) [paper]
• EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning (ACL 2025) [paper] [code]
• DAPO: Decoupled Clip and Dynamic Sampling Policy Optimization (arXiv 2025) [paper]
• MARFT: Multi-Agent Reinforcement Fine-Tuning (arXiv 2025) [paper] [code]

• ReFT: Reasoning with Reinforced Fine-Tuning (ACL 2024) [paper] [code]
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments (arXiv 2024) [paper] [code]
• AGILE: A Novel Reinforcement Learning Framework of LLM Agents (NeurIPS 2024) [paper] [code]
• Re-ReST: Reflection-Reinforced Self-Training for Language Agents (EMNLP 2024) [paper] [code]
• AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback (NeurIPS 2024) [paper] [code]
• Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents (ACL 2024) [paper] [code]
• OPTIMA: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System (arXiv 2024) [paper] [code]
• Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement (EMNLP 2024) [paper] [code]
• Retrospex: Language Agent Meets Offline Reinforcement Learning Critic (EMNLP 2024) [paper] [code]
• ENVISION:Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models (arXiv 2024) [paper] [code]
• DITS: Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search (arXiv 2025) [paper]

• Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks (NeurIPS 2024) [paper] [code]
• Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents (arXiv 2024) [paper]
• ExpeL: LLM Agents Are Experiential Learners (AAAI 2024) [paper] [code]
• AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning (NeurIPS 2024) [paper] [code]
• AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents (NeurIPS 2024) [paper]
• Experiential Co-Learning of Software-Developing Agents (ACL 2024) [paper] [code]

• Reflexion: Language Agents with Verbal Reinforcement Learning (NeurIPS 2023) [paper] [code]
• QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback based Self-Correction (ACL 2024) [paper] [code]
• Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization (ACL 2024) [paper] [code]
• SAGE: Self-Evolving Agents with Reflective and Memory-Augmented Abilities (arXiv 2024) [paper]
• ReCon: Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling (ACL-findings 2024) [paper]
• Symbolic Learning Enables Self-Evolving Agents (arXiv 2024) [paper] [code]
• COPPR:Reflective Multi-Agent Collaboration based on Large Language Models (NeurIPS 2024) [paper]
• METAREFLECTION: Learning Instructions for Language Agents using Past Reflections (EMNLP 2024) [paper] [code]
• InteRecAgent: Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations (arXiv 2023) [paper] [code]
• NLRL: Natural Language Reinforcement Learning (arXiv 2024) [paper] [code]
• Chain-of-Experts: When LLMs Meet Complex Operation Research Problems (ICLR 2024) [paper] [code]
• Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization (arXiv 2024) [paper]
• SELF-TUNING: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching (arXiv 2024) [paper]
• OPRO: LARGE LANGUAGE MODELS AS OPTIMIZERS (ICLR 2024) [paper] [code]
• MPO: Boosting LLM Agents with Meta Plan Optimization (arXiv 2025) [paper]

• Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (EMNLP 2024) [paper] [code]
• AVATAR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval (NeurIPS 2024) [paper] [code]
• AUTOACT: Automatic Agent Learning from Scratch for QA via Self-Planning (ACL 2024) [paper] [code]
• TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage (arXiv 2023) [paper]
• Lyra: Orchestrating Dual Correction in Automated Theorem Proving (TMLR 2024) [paper] [code]
• Offline Training of Language Model Agents with Functions as Learnable Weights (arXiv 2024) [paper]
• VideoAgent: A Memory-Augmented Multimodal Agent for Video Understanding (ECCV 2024) [paper] [code]
• ALITA: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution (arXiv 2025) [paper] [code]
• Search-o1: Agentic Search-Enhanced Large Reasoning Models (arXiv 2025) [paper] [code]

• Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs (EMNLP 2024) [paper]
• RaDA: Retrieval-augmented Web Agent Planning with LLMs (ACL 2024-findings) [paper] [code]
• AutoRAG: Automated Framework for Optimization of Retrieval Augmented Generation Pipeline (arXiv 2024) [paper] [code]
• RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents (arXiv 2024) [paper] [code]
• MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance (arXiv 2024) [paper] [code]
• PaperQA: Retrieval-Augmented Generative Agent for Scientific Research (arXiv 2023) [paper] [code]
• Search-o1: Agentic Search-Enhanced Large Reasoning Models (arXiv 2025) [paper] [code]

• CAPO: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation (arXiv 2024) [paper]
• A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops (arXiv 2024) [paper] [code]
• Training Agents with Weakly Supervised Feedback from Large Language Models (arXiv 2024) [paper]
• Chatdev: Communicative Agents for Software Development (arXiv 2023) [paper] [code]
• MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework (arXiv 2023) [paper] [code]
• MapCoder: Multi-Agent Code Generation for Competitive Problem Solving (arXiv 2024) [paper] [code]
• A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration (COLM 2024) [paper] [code]
• Scaling Large-Language-Model-based Multi-Agent Collaboration (arXiv 2024) [paper] [code]
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors (arXiv 2023) [paper] [code]
• SMoA: Improving Multi-Agent Large Language Models with Sparse Mixture-of-Agents (arXiv 2024) [paper] [code]
• Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate (EMNLP 2024) [paper] [code]
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation (arXiv 2023) [paper] [code]

1. WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents (NeurIPS 2022) [paper] [code]
2. WebArena: A Realistic Web Environment for Building Autonomous Agents (arXiv 2024) [paper] [code]
3. Mind2Web: Towards a Generalist Agent for the Web (NeurIPS 2023 Spotlight) [paper] [code]
4. Reinforcement Learning on Web Interfaces using Workflow-Guided Exploration (ICLR 2018) [paper] [code]
5. ScienceWorld: Is your Agent Smarter than a 5th Grader? (EMNLP 2022) [paper] [code]
6. ALFWorld: Aligning Text and Embodied Environments for Interactive Learning (ICLR 2021) [paper] [code]
7. Building Cooperative Embodied Agents Modularly with Large Language Models (ICLR 2024) [paper] [code]
8. ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks (CVPR 2020) [paper] [code]
9. RLCard: A Toolkit for Reinforcement Learning in Card Games (AAAI-Workshop 2020) [paper] [code]
10. OpenSpiel: A Framework for Reinforcement Learning in Games (arXiv 2019) [paper] [code]
11. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (EMNLP 2018) [paper] [code]
12. StrategyQA: Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies (TACL 2021) [paper] [code]
13. mmlu:Measuring Massive Multitask Language Understanding (ICLR 2021) [paper] [code]
14. TruthfulQA: Measuring How Models Mimic Human Falsehoods (ACL 2022) [paper] [code]
15. TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension (ACL 2017) [paper]
16. PubMedQA: A Dataset for Biomedical Research Question Answering (EMNLP 2019) [paper] [code]
17. MuSiQue: Multihop Questions via Single-hop Question Composition (TACL 2022) [paper] [code]
18. Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps (COLING 2020) [paper] [code]
19. A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers (NAACL 2021) [paper] [code]
20. Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge (arXiv 2018) [paper] [code]
21. Training Verifiers to Solve Math Word Problems (arXiv 2021) [[paper] [code]
22. A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers (ACL 2020) [paper] [code]
23. mwp:Are NLP Models Really Able to Solve Simple Math Word Problems? (NAACL 2021) [paper] [code]
24. Measuring Mathematical Problem Solving with the MATH Dataset (NeurIPS 2021) [paper] [code]
25. T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step (ACL 2024) [paper] [code]
26. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs (ICLR 2024) [paper] [code]
27. MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback (ICLR 2024) [paper] [code]
28. API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs (EMNLP 2023) [paper] [code]
29. A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge (ECCV 2022) [paper] [code]
30. Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering (NeurIPS 2022) [paper] [code]
31. VQA: Visual Question Answering (ICCV 2015) [paper] [code]
32. EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding (NeurIPS 2023) [paper] [code]
33. NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR 2021) [paper] [code]
34. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? (ICLR 2024) [paper] [code]
35. Evaluating Large Language Models Trained on Code (arXiv 2021) [paper] [code]
36. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code (arXiv 2024) [paper] [code]
37. Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs (NeurIPS 2023) [paper] [code]
38. InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback (NeurIPS 2023) [paper] [code]

• AgentBench: Evaluating LLMs as Agents (ICLR 2024) [paper] [code]
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments (arXiv 2024) [paper] [code]
• Just-Eval: The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning (ICLR 2024) [paper] [code]
• StreamBench: Towards Benchmarking Continuous Improvement of Language Agents (NeurIPS 2024) [paper] [code]
• AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agent (NeurIPS 2024) [paper] [code]
• GAIA: A Benchmark for General AI Assistants (arXiv 2023) [paper] [code]
• Humanity’s Last Exam (arXiv 2025) [paper] [code]
• NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls (arXiv 2024) [paper] [code]
• MCP_RADAR: Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models (arXiv 2025) [paper] [code]

• Med-PaLM: Large language models encode clinical knowledge (Nature 2023) [paper]
• DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task (arXiv 2023) [paper] [code]
• BianQue: Balancing the Questioning and Suggestion Ability of Health LLMs with Multi-turn Health Conversations Polished by ChatGPT (arXiv 2023) [paper] [code]
• DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation (arXiv 2023) [paper] [code]
• ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning (BCB 2024) [paper] [code]
• MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning (ACL-findings 2024) [paper] [code]
• MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making (NeurIPS 2024) [paper] [code]
• Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents (arXiv 2024) [paper]
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator (COLING 2025) [paper] [code]
• KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis (AAAI-25 Bridge Program) [paper]
• AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning (arXiv 2024) [paper] [code]
• MMedAgent: Learning to Use Medical Tools with Multi-modal Agent (EMNLP-findings 2024) [paper] [code]
• HuatuoGPT-o1: Towards Medical Complex Reasoning with LLMs (arXiv 2024) [paper] [code]
• IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment (arXiv 2025) [paper]

• CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis (arXiv 2024) [paper] [code]
• BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments (arXiv 2024) [paper] [code]
• ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning (Digital Discovery 2024) [paper] [code]
• CRISPR-GPT: An LLM Agent for Automated Design of Gene-Editing Experiments (arXiv 2024) [paper] [code]
• ChemCrow: Augmenting Large-Language Models with Chemistry Tools (Nature Machine Intelligence 2024) [paper] [code]
• DrugAssist: A Large Language Model for Molecule Optimization (Briefings in Bioinformatics 2024) [paper] [code]
• Agent-based Learning of Materials Datasets from Scientific Literature (Digital Discovery 2024) [paper] [code]
• DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration (arXiv 2024) [paper] [code]
• MProt-DPO: Breaking the ExaFLOPS Barrier for Multimodal Protein Design Workflows with Direct Preference Optimization (SC 2024) [paper]
• Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System (arXiv 2024) [paper] [code]
• SciAgent: Tool-augmented Language Models for Scientific Reasoning (arXiv 2024) [paper]

• Building Cooperative Embodied Agents Modularly with Large Language Models (ICLR 2024) [paper] [code]
• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (PMLR 2023) [paper] [code]
• RoCo: Dialectic Multi-Robot Collaboration with Large Language Models (ICRA 2024) [paper] [code]
• Voyager: An Open-Ended Embodied Agent with Large Language Models (arXiv 2023) [paper] [code]
• MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World (CVPR 2024) [paper] [code]
• Retrospex: Language Agent Meets Offline Reinforcement Learning Critic (EMNLP 2024) [paper] [code]
• EPO: Hierarchical LLM Agents with Environment Preference Optimization (EMNLP 2024) [paper] [code]
• AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning (NeurIPS 2024) [paper] [code]
• MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making (EMNLP 2024) [paper]
• iVideoGPT: Interactive VideoGPTs are Scalable World Models (NeurIPS 2024) [paper] [code]
• AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents (arXiv 2024) [paper]
• Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld (CVPR 2024) [paper] [code]

• Large Language Model Agent in Financial Trading: A Survey (arXiv 2024) [paper]
• TradingGPT: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance (arXiv 2023) [paper]
• FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design (AAAI-SS) [paper] [code]
• A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist (SIGKDD 2024) [paper]
• Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models (WWW 2024) [paper] [code]
• FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making (NeurIPS 2024) [paper]
• TradingAgents: Multi-Agents LLM Financial Trading Framework (arXiv 2024) [paper] [code]
• FinVision: A Multi-Agent Framework for Stock Market Prediction (ICAIF 2024) [paper]
• Simulating Financial Market via Large Language Model-based Agents (arXiv 2024) [paper]
• FinVerse: An Autonomous Agent System for Versatile Financial Analysis (arXiv 2024) [paper]
• FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models (arXiv 2024) [paper] [code]

• Agents in Software Engineering: Survey, Landscape, and Vision (arXiv 2024) [paper] [code]
• Large Language Model-Based Agents for Software Engineering: A Survey (arXiv 2024) [paper] [code]
• Chatdev: Communicative Agents for Software Development (ACL 2024) [paper] [code]
• MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework (ICLR 2024) [paper] [code]
• MapCoder: Multi-Agent Code Generation for Competitive Problem Solving (ACL 2024) [paper] [code]
• Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization (arXiv 2024) [paper] [code]
• Multi-Agent Software Development through Cross-Team Collaboration (arXiv 2024) [paper] [code]
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering (NeurIPS 2024) [paper] [code]
• CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges (ACL 2024) [paper]
• AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation (arXiv 2023) [paper] [code]
• RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning (arXiv 2024) [paper]
• Lemur: Harmonizing Natural Language and Code for Language Agents (ICLR 2024) [paper] [code]
• AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology (FORGE 2025) [paper] [code]

If you find this project or the related paper helpful, please consider citing our work:

A Survey on the Optimization of Large Language Model-based Agents 📚 arXiv:2503.12434

@article{du2025survey,
  title={A Survey on the Optimization of Large Language Model-based Agents},
  author={Du, Shangheng and Zhao, Jiabao and Shi, Jinxin and Xie, Zhentao and Jiang, Xin and Bai, Yanhong and He, Liang},
  journal={arXiv preprint arXiv:2503.12434},
  year={2025}
}