# UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems

arXiv: https://arxiv.org/abs/2605.26646 · HTML: https://mlsanity.com/paper/2605.26646/

## Key facts

- Cited by 6 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 24 of its 31 references that are in the map.
- First posted on arXiv 26 May 2026.

## 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, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (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)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [TACO: Topics in Algorithmic COde generation dataset](https://mlsanity.com/paper/2312.14852/) (2023)
- [Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2501.15228/) (2025)
- [Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs](https://mlsanity.com/paper/2510.11062/) (2025)
- [Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems](https://mlsanity.com/paper/2602.08847/) (2026)
- [Heterogeneous Agent Collaborative Reinforcement Learning](https://mlsanity.com/paper/2603.02604/) (2026)
- [Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search](https://mlsanity.com/paper/2601.04703/) (2026)
- [MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.01005/) (2025)
- [JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG](https://mlsanity.com/paper/2601.21916/) (2026)

## Built on by (most cited first, 6 of 6)

- [RaMem: Contextual Reinstatement for Long-term Agentic Memory](https://mlsanity.com/paper/2606.22844/) (2026)
- [SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task](https://mlsanity.com/paper/2607.24850/) (2026)
- [MIRROR: Learning from the Other View for Multi-Modal Reasoning](https://mlsanity.com/paper/2607.21552/) (2026)
- [SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2610.11345/) (2026)
- [GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs](https://mlsanity.com/paper/2609.12265/) (2026)
- [Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems](https://mlsanity.com/paper/2610.01042/) (2026)

## Abstract (arXiv)

LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely optimized through a unified reinforcement learning interface. Existing RL post-training frameworks mainly target single-policy optimization and lack abstractions for user-defined multi-agent workflows, structured interaction, role-specific credit assignment, and configurable parameter sharing. We present UnityMAS-O, a general RL optimization framework for LLM-based multi-agent systems. UnityMAS-O treats the complete workflow as the optimization unit, rather than a single response or policy trajectory. It represents workflows through four first-class objects: logical agent roles, graph trajectories, user-defined rewards, and agent--model mappings. This decouples logical agents from physical model parameters, supporting full sharing, full separation, and partial sharing, with rewards assigned at role, turn, and trajectory levels. UnityMAS-O extends verl with a Ray-based star-topology runtime. A central controller executes workflows, invokes tools, records structured trajectories, and assembles rewards; model-local worker groups handle rollout, buffering, advantage computation, and distributed PPO-style updates. Users can define agents, workflows, model mappings, and rewards without rewriting the optimization infrastructure. We instantiate UnityMAS-O on retrieval-augmented QA, iterative agentic search, and reflective code generation. Across Natural Questions, HotpotQA, and held-out code tasks, multi-agent RL improves manually specified workflows after optimization, with especially large gains for smaller models and strict code all-passed metrics. These results show that UnityMAS-O can serve as a reusable substrate for converting diverse LLM-based multi-agent workflows into trainable multi-agent RL systems.