Papers

Stream of Belief:用潜在信念动力学提升多智能体推理

Stream of Belief: Eliciting Collective Intelligence through Latent Belief Dynamics

Why we picked it

一篇方法论论文:SoB 让多个智能体维护连续潜在信念并迭代收敛,而不是轮流发文本消息。相比常见的辩论、投票式多智能体框架,它给出了更形式化的停止标准。做智能体框架研究或多智能体系统开发的人可以看看通信机制怎么设计。

论文提出 Stream of Belief(SoB),把多智能体推理重新表述为一个隐性信念动力学寻找集体均衡的过程。

Body

每个智能体不再只输出离散文本消息,而是维护连续的潜在信念(latent beliefs),通过通信与反思反复迭代更新这些信念。SoB 的终止条件被定义为一个集体信念状态:当继续通信不再产生有意义的信息传播时,系统即达到均衡。

作者报告在多个任务和多个模型家族上验证了 SoB 的泛化能力,并主张从信念动力学的视角来扩展多智能体推理。论文全文可在 arXiv(编号 2611.

21250)查阅。

Original · arXiv cs.AI

Stream of Belief: Eliciting Collective Intelligence through Latent Belief Dynamics

In this work, we view multi-agent reasoning as a process of seeking a collective equilibrium of implicit belief dynamics and introduce Stream of Belief (SoB), where agents maintain continuous latent beliefs and iteratively refine them through communication and reflection. Our method seeks a collective belief state of a multi-agent system where further communication induces no meaningful information propagation. Through extensive experiments, we demonstrate the generalization of SoB across tasks and model families. More Broadly, our results suggest a new perspective on scaling multi-agent reasoning from belief dynamics.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include multi-agent systems, reasoning models, papers, Stream of Belief.

Source attribution: curated from arXiv cs.AI (@Yu Yao, Jiayi Dong, Yilun Du).