mlsanityData to 7 Oct 2026

MPO: Boosting LLM Agents with Meta Plan Optimization

arXiv 2503.02682 ↗First posted 4 Mar 2025cs.CL cs.AI cs.LGcited by 36

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Recent advancements in large language models (LLMs) have enabled LLM-based agents to successfully tackle interactive planning tasks. However, despite their successes, existing approaches often suffer from planning hallucinations and require retraining for each new agent. To address these challenges, we propose the Meta Plan Optimization (MPO) framework, , which enhances agent planning capabilities by directly incorporating explicit guidance. Unlike previous methods that rely on complex knowledge, which either require significant human effort or lack quality assurance, MPO leverages high-level general guidance through meta plans to assist agent planning and enables continuous optimization of the meta plans based on feedback from the agent's task execution. Our experiments conducted on two representative tasks demonstrate that MPO significantly outperforms existing baselines. Moreover, our analysis indicates that MPO provides a plug-and-play solution that enhances both task completion efficiency and generalization capabilities in previous unseen scenarios.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 32 of its 39 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

32 of 39 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories10 Oct
  2. 2024Tree Search for Language Model Agents1 Jul
  3. 2024Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement17 Jun
  4. 2024Agent Planning with World Knowledge Model23 May
  5. 2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents13 Mar
  6. 2024Understanding the planning of LLM agents: A survey5 Feb
  7. 2024AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback2 Feb
  8. 2024Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents1 Feb
  9. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs19 Oct
  10. 2023Agents: An Open-source Framework for Autonomous Language Agents14 Sep
  11. 2023ExpeL: LLM Agents Are Experiential Learners20 Aug

Other references · 21

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  8. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  10. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
  11. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  12. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
9 more
  1. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  2. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  3. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  4. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 350
  5. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  6. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  7. 2024EPO: Hierarchical LLM Agents with Environment Preference Optimizationcited by 28
  8. 2023ProAgent: From Robotic Process Automation to Agentic Process Automationcited by 26
  9. 2022Few-shot Subgoal Planning with Language Modelscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 16; 2026: 20.

36 papers.

Sort:

By area:

  1. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 129
  2. 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agentscited by 66
  3. 2025Deep Research: A Survey of Autonomous Research Agentscited by 63
  4. 2026Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agentscited by 57
  5. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  6. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  7. 2025ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflectioncited by 30
  8. 2025PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaborationcited by 25
  9. 2025A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Taskscited by 17
  10. 2025SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agentscited by 15
  11. 2025SAND: Boosting LLM Agents with Self-Taught Action Deliberationcited by 14
  12. 2025ReCode: Unify Plan and Action for Universal Granularity Controlcited by 14
24 more
  1. 2025PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learningcited by 11
  2. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  3. 2026Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agentscited by 9
  4. 2026RoboAgent: Chaining Basic Capabilities for Embodied Task Planningcited by 6
  5. 2025Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planningcited by 4
  6. 2025Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanismcited by 4
  7. 2026TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agentscited by 4
  8. 2026Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Modelscited by 3
  9. 2026RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergycited by 3
  10. 2026Self-evolving LLM agents with in-distribution Optimizationcited by 3
  11. 2025More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agentscited by 2
  12. 2026Environment-Grounded Automated Prompt Optimization for LLM Game Agentscited by 2
  13. 2026Helix: A Dual-Helix Co-Evolutionary Multi-Agent System for Prompt Optimization and Question Reformulationcited by 1
  14. 2026Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agentscited by 1
  15. 2025Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agentscited by 0
  16. 2026PRISM: Learning Design Knowledge from Data for Stylistic Design Improvementcited by 0
  17. 2026From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agentscited by 0
  18. 2026MA2P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasioncited by 0
  19. 2026Unified Context Evolution for LLM Agentscited by 0
  20. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modescited by 0
  21. 2026PersonalPlan: Planning Multi-Agent Systems for Personalized Programming Learningcited by 0
  22. 2026Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproductioncited by 0
  23. 2026Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videoscited by 0
  24. 2026SGG-ReflAct: Sub-Goal Guided ReflAct with Structured Planning for Reliable Long-Horizon Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
  2. 2026Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning
  3. 2025Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
  4. 2026MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
  5. 2024CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation
  6. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
  7. 2026PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs
  8. 2024Query-Efficient Planning with Language Models