arXiv cs.AI· Jin Gao·· 12 小时前AI 评分26
如何衡量 AI 智能体网络中的共识形成
Measuring Consensus in AI Agent Networks
AI 导读
研究提出一个评估框架，将 AI 智能体的共识形成视为公开立场向共同区域演化的过程，并追踪立场轨迹、群体离散度与公开消息中的信息。基于 1,872 次完整运行的实验显示，分享解释与更准确的群体决策相关，而涉及重复信息与已取消合同的任务虽聚合答案准确，智能体间仍存在持续分歧。
正文 · 原文
Abstract:As AI agents become increasingly connected through networks and take on tasks that require negotiation and joint decision-making, a systematic approach is needed to assess how their views converge and what information supports their decisions. We present an evaluation framework that treats consensus formation as the evolution of publicly stated positions toward a shared region, using accumulated communication history as context. The framework tracks position trajectories, group dispersion, and information expressed in public messages. Two case studies examine staffing decisions based on distributed facts and decisions requiring agents to reconcile duplicate information and a cancelled contract. Results from 1,872 completed runs associate sharing explanations with more accurate group decisions, while the second task reveals persistent disagreement despite accurate aggregate answers. Membership-change experiments provide a complementary evaluation. By separating convergence among agents from progress toward a task's full-information answer, the framework relates decision accuracy and bounded disagreement to the information available during the exchange.
| Comments: | 4 pages. Accepted at the NANDA Workshop, IEEE TPS-ISA 2026 |
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.24833 [cs.MA] |
| (or arXiv:2610.24833v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.24833 arXiv-issued DOI via DataCite |
Submission history
From: Jin Gao [view email]
[v1]
Sat, 17 Oct 2026 19:29:07 UTC (204 KB)
来源：arXiv cs.AI · arxiv.org