# MPO: Boosting LLM Agents with Meta Plan Optimization

arXiv: https://arxiv.org/abs/2503.02682 · HTML: https://mlsanity.com/paper/2503.02682/

## Key facts

- Cited by 36 papers in the map (data through 14 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.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [Tree Search for Language Model Agents](https://mlsanity.com/paper/2407.01476/) (2024)
- [RestGPT: Connecting Large Language Models with Real-World RESTful APIs](https://mlsanity.com/paper/2306.06624/) (2023)
- [Agents: An Open-source Framework for Autonomous Language Agents](https://mlsanity.com/paper/2309.07870/) (2023)
- [Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement](https://mlsanity.com/paper/2406.11176/) (2024)
- [AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents](https://mlsanity.com/paper/2403.08978/) (2024)
- [Agent Planning with World Knowledge Model](https://mlsanity.com/paper/2405.14205/) (2024)
- [AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories](https://mlsanity.com/paper/2410.07706/) (2024)
- [Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents](https://mlsanity.com/paper/2402.00798/) (2024)
- [EPO: Hierarchical LLM Agents with Environment Preference Optimization](https://mlsanity.com/paper/2408.16090/) (2024)
- [ProAgent: From Robotic Process Automation to Agentic Process Automation](https://mlsanity.com/paper/2311.10751/) (2023)

## Built on by (most cited first, 30 of 36)

- [OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation](https://mlsanity.com/paper/2505.23885/) (2025)
- [SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents](https://mlsanity.com/paper/2508.02085/) (2025)
- [Deep Research: A Survey of Autonomous Research Agents](https://mlsanity.com/paper/2508.12752/) (2025)
- [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://mlsanity.com/paper/2604.06132/) (2026)
- [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025)
- [A Survey on the Optimization of Large Language Model-based Agents](https://mlsanity.com/paper/2503.12434/) (2025)
- [ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection](https://mlsanity.com/paper/2505.15182/) (2025)
- [PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration](https://mlsanity.com/paper/2505.15047/) (2025)
- [A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks](https://mlsanity.com/paper/2510.05608/) (2025)
- [SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents](https://mlsanity.com/paper/2506.21669/) (2025)
- [ReCode: Unify Plan and Action for Universal Granularity Control](https://mlsanity.com/paper/2510.23564/) (2025)
- [SAND: Boosting LLM Agents with Self-Taught Action Deliberation](https://mlsanity.com/paper/2507.07441/) (2025)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning](https://mlsanity.com/paper/2508.00344/) (2025)
- [Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents](https://mlsanity.com/paper/2601.07577/) (2026)
- [RoboAgent: Chaining Basic Capabilities for Embodied Task Planning](https://mlsanity.com/paper/2604.07774/) (2026)
- [Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning](https://mlsanity.com/paper/2508.03018/) (2025)
- [Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism](https://mlsanity.com/paper/2510.13170/) (2025)
- [TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents](https://mlsanity.com/paper/2602.19633/) (2026)
- [Self-evolving LLM agents with in-distribution Optimization](https://mlsanity.com/paper/2606.07367/) (2026)
- [More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents](https://mlsanity.com/paper/2506.21967/) (2025)
- [Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models](https://mlsanity.com/paper/2603.13985/) (2026)
- [RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy](https://mlsanity.com/paper/2603.17831/) (2026)
- [Environment-Grounded Automated Prompt Optimization for LLM Game Agents](https://mlsanity.com/paper/2606.17838/) (2026)
- [Helix: A Dual-Helix Co-Evolutionary Multi-Agent System for Prompt Optimization and Question Reformulation](https://mlsanity.com/paper/2603.19732/) (2026)
- [Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents](https://mlsanity.com/paper/2604.17019/) (2026)
- [From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents](https://mlsanity.com/paper/2604.23194/) (2026)
- [Unified Context Evolution for LLM Agents](https://mlsanity.com/paper/2606.02304/) (2026)
- [Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos](https://mlsanity.com/paper/2608.26355/) (2026)
- [Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agents](https://mlsanity.com/paper/2512.24461/) (2025)

## 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.