mlsanityData to 14 Oct 2026

Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach

arXiv 2509.16736 ↗First posted 20 Sep 2025cs.MA cs.CRcited by 12

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Large Language Models (LLMs) have enabled the emergence of autonomous agents capable of complex reasoning, planning, and interaction. However, coordinating such agents at scale remains a fundamental challenge, particularly in decentralized environments where communication lacks transparency and agent behavior cannot be shaped through centralized incentives. We propose a blockchain-based framework that enables transparent agent registration, verifiable task allocation, and dynamic reputation tracking through smart contracts. The core of our design lies in two mechanisms: a matching score-based task allocation protocol that evaluates agents by reputation, capability match, and workload; and a behavior-shaping incentive mechanism that adjusts agent behavior via feedback on performance and reward. Our implementation integrates GPT-4 agents with Solidity contracts and demonstrates, through 50-round simulations, strong task success rates, stable utility distribution, and emergent agent specialization. The results underscore the potential for trustworthy, incentive-compatible multi-agent coordination in open environments.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 40 of its 74 references that are in the map. First posted on arXiv 20 Sep 2025.

Builds on

40 of 74 references.

References · 40

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2023Let's Verify Step by Stepcited by 3,789
  3. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  4. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  5. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  6. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  7. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  8. 2024Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Expertscited by 376
  9. 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Studycited by 262
  10. 2023Self-collaboration Code Generation via ChatGPTcited by 258
  11. 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 237
  12. 2023Playing repeated games with Large Language Modelscited by 217
28 more
  1. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
  2. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 172
  3. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
  4. 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Modelscited by 153
  5. 2025DataSentinel: A Game-Theoretic Detection of Prompt Injection Attackscited by 143
  6. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 134
  7. 2024Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methodscited by 116
  8. 2022Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproductioncited by 111
  9. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 106
  10. 2023Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generationcited by 105
  11. 2023Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysiscited by 92
  12. 2024β-DPO: Direct Preference Optimization with Dynamic βcited by 90
  13. 2025Interactive Debugging and Steering of Multi-Agent AI Systemscited by 68
  14. 2024ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learningcited by 64
  15. 2024MACRec: a Multi-Agent Collaboration Framework for Recommendationcited by 58
  16. 2024AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent Systemcited by 53
  17. 2024Learning Multi-Agent Communication from Graph Modeling Perspectivecited by 48
  18. 2024AGILE: A Novel Reinforcement Learning Framework of LLM Agentscited by 45
  19. 2024Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learningcited by 23
  20. 2025AgentFM: Role-Aware Failure Management for Distributed Databases with LLM-Driven Multi-Agentscited by 19
  21. 2023Fine-Tuning Games: Bargaining and Adaptation for General-Purpose Modelscited by 17
  22. 2024Human vs. Generative AI in Content Creation Competition: Symbiosis or Conflict?cited by 13
  23. 2025LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generationcited by 13
  24. 2023Attention-Guided Contrastive Role Representations for Multi-Agent Reinforcement Learningcited by 11
  25. 2025LLM-Net: Democratizing LLMs-as-a-Service through Blockchain-based Expert Networkscited by 7
  26. 2025BESA: Boosting Encoder Stealing Attack with Perturbation Recoverycited by 2
  27. 2024SoK: Bitcoin Layer Two (L2)cited by 1
  28. 2025Epass: Efficient and Privacy-Preserving Asynchronous Payment on Blockchaincited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 9.

12 papers.

  1. 2025The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerabilitycited by 12
  2. 2026Learning Decentralized LLM Collaboration with Multi-Agent Actor Criticcited by 8
  3. 2026Internet of Agentic AI: Incentive-Compatible Distributed Teaming and Workflowcited by 8
  4. 2025DAO-Agent: Zero Knowledge-Verified Incentives for Decentralized Multi-Agent Coordinationcited by 3
  5. 2026AgentCity: Constitutional Governance for Autonomous Agent Economies via Separation of Powercited by 3
  6. 2025Does GenAI Rewrite How We Write? An Empirical Study on Two-Million Preprintscited by 2
  7. 2026Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directionscited by 1
  8. 2026When Should Agent Trust Be Conditional? Characterizing and Attacking Skill-Conditional Reputation in Agent Swarmscited by 0
  9. 2026A Diagnostic Framework for AI Agent Behaviorcited by 0
  10. 2026ChainClaw: A Layered Agent Framework for Reliable On-Chain Executioncited by 0
  11. 2026DART: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance for Trustworthy LLM Multi-Agent Collaborationcited by 0
  12. 2026Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applicationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions
  2. 2024LLM Multi-Agent Systems: Challenges and Open Problems
  3. 2025Decentralized Multi-Agent System with Trust-Aware Communication
  4. 2026Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries
  5. 2025Byzantine-Robust Decentralized Coordination of LLM Agents
  6. 2025From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems
  7. 2025Fetch.ai: An Architecture for Modern Multi-Agent Systems
  8. 2025BlockA2A: Towards Secure and Verifiable Agent-to-Agent Interoperability