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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Qi, Minfeng, Zhu, Tianqing, Zhang, Lefeng, Li, Ningran, Zhou, Wanlei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912596215463936
author Qi, Minfeng
Zhu, Tianqing
Zhang, Lefeng
Li, Ningran
Zhou, Wanlei
author_facet Qi, Minfeng
Zhu, Tianqing
Zhang, Lefeng
Li, Ningran
Zhou, Wanlei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16736
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
Qi, Minfeng
Zhu, Tianqing
Zhang, Lefeng
Li, Ningran
Zhou, Wanlei
Multiagent Systems
Cryptography and Security
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.
title Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
topic Multiagent Systems
Cryptography and Security
url https://arxiv.org/abs/2509.16736