arXiv cs.MA· Isabel Jones, Matthew Edwards, Janina A. Hoffmann·· 3 天前AI 评分24
竞争激励下 LLM 共识形成的驱动因素：一项模拟研究
Drivers of LLM Consensus Formation Under Competing Incentives: A Simulation Study
AI 导读
一项基于 Network Consensus 游戏的模拟研究评估了 LLM 在竞争激励下达成共识的机制，测试了六个开源模型和 ChatGPT 5.6-sol。开源 LLM 达成共识的频率低于人类，且仅在消息可全网传播时才能实现；ChatGPT 5.6-sol 则能在仅与邻居通信甚至无通信能力时达成共识，这得益于其更低的固执性和更高的从众倾向。
正文 · 原文
Abstract:Large Language Models (LLMs) are increasingly deployed in multi-agent environments that produce unanimous agreement, both in intended interactions that need coordination and in unintended emergent interactions. Consequently, understanding how LLMs with competing incentives reach consensus is crucial to better interpret and design LLM collectives. We introduce an evaluation, based on the Network Consensus game, to assess the mechanisms driving this process. Here, a network of agents must agree on one of two colours to receive a payoff, but agents are offered different payoffs for the agreed colour. We vary components such as communication access and network structure and assess six open-source models and one closed model (ChatGPT 5.6-sol).
We find that open-source LLMs reach consensus less often than humans in comparable experiments and only if messages are communicated across the global network. ChatGPT 5.6-sol, however, is able to reach consensus with communication limited to its neighbours and with no communication ability. This is achieved through lower stubbornness and higher majority-following tendencies, and by providing more information about its neighbours' states in messages. However, situating agents in a highly clustered graph reduces consensus, regardless of these traits, demonstrating that both system design and individual model traits drive collective outcomes.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.20200 [cs.AI] |
| (or arXiv:2610.20200v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20200 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Isabel Jones [view email]
[v1]
Wed, 14 Oct 2026 13:46:42 UTC (5,092 KB)
来源：arXiv cs.MA · arxiv.org