# Multi-agent Collaboration with State Management

arXiv: https://arxiv.org/abs/2605.20563 · HTML: https://mlsanity.com/paper/2605.20563/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 19 May 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 25 of 25)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion](https://mlsanity.com/paper/2310.11248/) (2023)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023)
- [HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://mlsanity.com/paper/2408.09559/) (2024)
- [DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories](https://mlsanity.com/paper/2405.19856/) (2024)
- [CodeScore: Evaluating Code Generation by Learning Code Execution](https://mlsanity.com/paper/2301.09043/) (2023)
- [SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution](https://mlsanity.com/paper/2507.23348/) (2025)
- [Commit0: Library Generation from Scratch](https://mlsanity.com/paper/2412.01769/) (2024)
- [RepoFusion: Training Code Models to Understand Your Repository](https://mlsanity.com/paper/2306.10998/) (2023)
- [Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute](https://mlsanity.com/paper/2503.23803/) (2025)
- [Effective Strategies for Asynchronous Software Engineering Agents](https://mlsanity.com/paper/2603.21489/) (2026)
- [ROCODE: Integrating Backtracking Mechanism and Program Analysis in Large Language Models for Code Generation](https://mlsanity.com/paper/2411.07112/) (2024)
- [CodeCRDT: Observation-Driven Coordination for Multi-Agent LLM Code Generation](https://mlsanity.com/paper/2510.18893/) (2025)
- [AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering](https://mlsanity.com/paper/2604.13120/) (2026)
- [Think Anywhere in Code Generation](https://mlsanity.com/paper/2603.29957/) (2026)
- [From I/O to Code with Discovery Agent](https://mlsanity.com/paper/2605.15334/) (2026)

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

- [CoAgent: Concurrency Control for Multi-Agent Systems](https://mlsanity.com/paper/2606.15376/) (2026)
- [ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis](https://mlsanity.com/paper/2607.00041/) (2026)
- [Agensh: Scaling Organizational Intelligence to 1,024 Agents](https://mlsanity.com/paper/2609.26781/) (2026)
- [OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime](https://mlsanity.com/paper/2609.38345/) (2026)
- [When Agent Context Goes Stale: Incoherence in Volatile Agent Context](https://mlsanity.com/paper/2610.05281/) (2026)
- [Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents](https://mlsanity.com/paper/2610.18082/) (2026)

## Abstract (arXiv)

Recent advances in multi-agent systems have shown great potential for solving complex tasks. However, when multiple agents edit a shared codebase concurrently, their changes can silently conflict and inconsistent views lead to integration failures. Existing multi-agent systems address this through workspace isolation (e.g., one git worktree per agent), but this defers conflict resolution to a post-hoc merge step where recovery is expensive. In this paper, we propose STORM, i.e., STate-ORiented Management for multi-agent collaboration. Specifically, STORM manages agent states by mediating their interactions with the shared workspace, ensuring that each agent operates on a consistent view of the codebase and that conflicting edits are detected and resolved at write time. We evaluate STORM on Commit0 and PaperBench across multiple LLMs. STORM outperforms the git-worktree-based multi-agent baseline by +18.7 on Commit0-Lite and +1.4 on PaperBench, while achieving comparable or better cost efficiency. Combined with single-agent runs, STORM reaches highest scores of 87.6 and 78.2 on the two benchmarks respectively, suggesting that explicit state management is a more effective foundation for multi-agent collaboration than workspace isolation. STORM can also be plugged into any multi-agent system seamlessly.