# Multi-Agent Tool-Integrated Policy Optimization

arXiv: https://arxiv.org/abs/2510.04678 · HTML: https://mlsanity.com/paper/2510.04678/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 17 of 17)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [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)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [WebSailor: Navigating Super-human Reasoning for Web Agent](https://mlsanity.com/paper/2507.02592/) (2025)
- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [ToRL: Scaling Tool-Integrated RL](https://mlsanity.com/paper/2503.23383/) (2025)
- [SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning](https://mlsanity.com/paper/2509.02479/) (2025)
- [Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework](https://mlsanity.com/paper/2305.03268/) (2023)
- [Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources](https://mlsanity.com/paper/2305.13269/) (2023)
- [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025)
- [Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?](https://mlsanity.com/paper/2410.23856/) (2024)
- [Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks](https://mlsanity.com/paper/2410.01428/) (2024)

## Built on by (most cited first, 16 of 16)

- [LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling](https://mlsanity.com/paper/2511.20785/) (2025)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO](https://mlsanity.com/paper/2511.13288/) (2025)
- [Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems](https://mlsanity.com/paper/2602.08847/) (2026)
- [The Interplay of Harness Design and Post-Training in LLM Agents](https://mlsanity.com/paper/2606.25447/) (2026)
- [Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI](https://mlsanity.com/paper/2510.16720/) (2025)
- [Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System](https://mlsanity.com/paper/2602.08335/) (2026)
- [PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting](https://mlsanity.com/paper/2606.08878/) (2026)
- [Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces](https://mlsanity.com/paper/2605.02801/) (2026)
- [Agentic Tool Use in Large Language Models](https://mlsanity.com/paper/2604.00835/) (2026)
- [ICRL: Learning to Internalize Self-Critique with Reinforcement Learning](https://mlsanity.com/paper/2605.15224/) (2026)
- [EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management](https://mlsanity.com/paper/2606.03841/) (2026)
- [APEx: Distillation of Agent Procedural Experience for Adaptive Deep Research Question Answering](https://mlsanity.com/paper/2609.02253/) (2026)
- [WikiLoop: Jointly Learning to Build and Navigate Agent-Native Wikis with Downstream Feedback](https://mlsanity.com/paper/2607.26604/) (2026)
- [ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models](https://mlsanity.com/paper/2608.11949/) (2026)
- [SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs](https://mlsanity.com/paper/2609.08452/) (2026)

## Abstract (arXiv)

Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks. Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses. A natural solution is to adopt a multi-agent framework with planner- and worker-agents to manage context. However, no existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks. To address this gap, we propose Multi-Agent Tool-Integrated Policy Optimization (MATPO), which enables distinct roles (planner and worker) to be trained within a single LLM instance using role-specific prompts via reinforcement learning. MATPO is derived from a principled credit assignment mechanism across planner and worker rollouts. This design eliminates the need to deploy multiple LLMs, which would be memory-intensive, while preserving the benefits of specialization. Experiments on GAIA-text, WebWalkerQA, and FRAMES show that MATPO consistently outperforms single-agent baselines by an average of 18.38% relative improvement in performance and exhibits greater robustness to noisy tool outputs. Our findings highlight the effectiveness of unifying multiple agent roles within a single LLM and provide practical insights for stable and efficient multi-agent RL training.