mlsanityData to 7 Oct 2026

Reinforced Collaboration in Multi-Agent Flow Networks

arXiv 2605.12943 ↗First posted 13 May 2026cs.LGcited by 0

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

Abstract (arXiv)

Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation, arising from suboptimal workflow design or inaccurate agent outputs, which can propagate through the agent collaboration process and degrade final results. To address the challenges, we present MANGO (Multi-Agent Network Gradient Optimization), a data-driven framework that organizes and refines agent collaboration via a flow network constructed from past successful workflows. MANGO integrates reinforcement learning and textual gradients to jointly optimize workflow paths and agent behaviors, while a skipping mechanism prevents redundant updates to well-optimized agents for improving efficiency. Extensive experiments on seven benchmarks show that MANGO achieves up to 12.8% performance improvement over state-of-the-art baselines, enhances efficiency by 47.4%, and generalizes effectively to unseen domains. Our code and datasets are publicly available at https://github.com/openJiuwen-ai/agent-store/tree/main/community/mango.

Key facts. No citing papers in the map yet (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 52 of its 74 references that are in the map. First posted on arXiv 13 May 2026.

Builds on

52 of 74 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025Augmented Runtime Collaboration for Self-Organizing Multi-Agent Systems: A Hybrid Bi-Criteria Routing Approach30 Nov
  2. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search6 Jun
  3. 2025Multi-Agent Collaboration via Evolving Orchestration26 May
  4. 2025MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems5 Mar
  5. 2025Multi-agent Architecture Search via Agentic Supernet6 Feb
  6. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks15 Oct
  7. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Space8 Oct
  8. 2024Automated Design of Agentic Systems15 Aug
  9. 2024Symbolic Learning Enables Self-Evolving Agents26 Jun
  10. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms20 Jun
  11. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  12. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 40

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  8. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  9. 2021Program Synthesis with Large Language Modelscited by 3,509
  10. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  11. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  12. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
28 more
  1. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  2. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  4. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  5. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  6. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  7. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  8. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  9. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wildcited by 505
  10. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  11. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 377
  12. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  13. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 220
  14. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  15. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  16. 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizingcited by 123
  17. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agentscited by 102
  18. 2025MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learningcited by 80
  19. 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 73
  20. 2025MARFT: Multi-Agent Reinforcement Fine-Tuningcited by 51
  21. 2025LLM Collaboration With Multi-Agent Reinforcement Learningcited by 47
  22. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  23. 2023ChatLLM Network: More brains, More intelligencecited by 37
  24. 2025Self-Supervised Prompt Optimizationcited by 37
  25. 2025PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learningcited by 11
  26. 2025InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planningcited by 8
  27. 2025DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspectivecited by 7
  28. 2025DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimizationcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking Multi-Agent Collaboration: When More Is Less
  2. 2026Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization
  3. 2026AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
  4. 2026An Empirical Study of Multi-Agent Collaboration for Automated Research
  5. 2026AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems
  6. 2025OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning
  7. 2026CollabFlow: Recursive Self-Improvement of Agent Collaboration
  8. 2025Reinforcement Learning-Augmented LLM Agents for Collaborative Decision Making and Performance Optimization