mlsanityData to 7 Oct 2026

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks

arXiv 2503.02390 ↗First posted 4 Mar 2025cs.MAcited by 30

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 2 more
Abstract (arXiv)

Multi-agent systems (MAS) have emerged as a promising approach for enhancing the reasoning capabilities of large language models in complex problem-solving; however, current MAS frameworks suffer from poor flexibility and scalability with underdeveloped optimization strategies. To address these challenges, we propose ReSo, which integrates task graph generation with a reward-driven two-stage agent selection process centered on our Collaborative Reward Model that provides fine-grained reward signals to optimize MAS cooperation. We also introduce an automated data synthesis framework for generating MAS benchmarks without any human annotations. Experimental results show that ReSo matches or outperforms existing methods, achieving 33.7 percent accuracy on Math-MAS and 32.3 percent accuracy on SciBench-MAS, where other approaches completely fail.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 51 of its 54 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

51 of 54 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024OpenAI o1 System Card21 Dec
  2. 2024MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning18 Sep
  3. 2024RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation15 Sep
  4. 2024Mixture-of-Agents Enhances Large Language Model Capabilities7 Jun
  5. 2024MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models2 Feb

Other references · 46

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  6. 2024Qwen2.5 Technical Reportcited by 4,713
  7. 2024GPT-4o System Cardcited by 4,467
  8. 2023Let's Verify Step by Stepcited by 3,598
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  10. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  11. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  12. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
34 more
  1. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  2. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  3. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  4. 2025s1: Simple test-time scalingcited by 1,311
  5. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  6. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  7. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  8. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  9. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
  10. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  11. 2024DeepSeek-V3 Technical Reportcited by 724
  12. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  13. 2024Improve Mathematical Reasoning in Language Models by Automated Process Supervisioncited by 426
  14. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  15. 2025The Lessons of Developing Process Reward Models in Mathematical Reasoningcited by 402
  16. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 338
  17. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 291
  18. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
  19. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 281
  20. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  21. 2023Self-collaboration Code Generation via ChatGPTcited by 255
  22. 2023SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Modelscited by 246
  23. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  24. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 200
  25. 2022Defining and Characterizing Reward Hackingcited by 184
  26. 2024AlphaMath Almost Zero: Process Supervision without Processcited by 160
  27. 2024O1 Replication Journey: A Strategic Progress Report -- Part 1cited by 140
  28. 2024LLM Multi-Agent Systems: Challenges and Open Problemscited by 119
  29. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 110
  30. 2024Language Agents as Optimizable Graphscited by 81
  31. 2024Reinforcement Learning Enhanced LLMs: A Surveycited by 69
  32. 2024Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervisioncited by 60
  33. 2024MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problemscited by 41
  34. 2024CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Taskscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 16; 2026: 14.

30 papers.

Sort:

By area:

  1. 2025RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Roboticscited by 125
  2. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 112
  3. 2025Latent Collaboration in Multi-Agent Systemscited by 67
  4. 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Modelscited by 35
  5. 2025X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMscited by 33
  6. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 27
  7. 2025VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learningcited by 18
  8. 2025Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learningcited by 18
  9. 2026Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judgecited by 16
  10. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  11. 2025Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMscited by 14
  12. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 12
18 more
  1. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 11
  2. 2026Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learningcited by 9
  3. 2026The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systemscited by 8
  4. 2025Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learningcited by 3
  5. 2025LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledgecited by 3
  6. 2026Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactionscited by 3
  7. 2025Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimizationcited by 2
  8. 2025Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferencescited by 2
  9. 2025Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Unitscited by 2
  10. 2025GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policiescited by 2
  11. 2026SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systemscited by 1
  12. 2026Beyond Sentiment: A Multi-Agent Pipeline for Actionable Business Advice from Reviewscited by 0
  13. 2026From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environmentscited by 0
  14. 2026Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futurescited by 0
  15. 2026LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systemscited by 0
  16. 2026ForestBench: A Unified Graph Framework for Evaluating Multi-Agent Collaborationcited by 0
  17. 2026ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Modelscited by 0
  18. 2026ChemDIRT: A Diversified Instruction, Representation, and Task Benchmark for Robust Chemistry-LLM Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
  2. 2025OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning
  3. 2025Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
  4. 2026Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning
  5. 2025SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning
  6. 2025AgentCDM: Enhancing Multi-Agent Collaborative Decision-Making via ACH-Inspired Structured Reasoning
  7. 2024Mars-PO: Multi-Agent Reasoning System Preference Optimization
  8. 2026AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization