Bayesian Chronicle Agents：LLM 智能体的可控信念层
Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents
做社会仿真的看这篇：BCA 用一个 κ 参数控制 LLM 智能体的固执程度，共识或分歧按需生成，还能审计偏差。
arXiv 论文提出 Bayesian Chronicle Agents（BCA），把智能体相信什么和怎么说分开，每条立场对应一个概率。智能体每听到一条发言就做一次贝叶斯更新，参数 κ 编码固执程度，设计参照 Friedkin–Johnsen（FJ）观点动力学。调节 κ 可按需生成共识、持续分歧、少数派影响三种典型动态，其中持续分歧与 FJ 闭式不动点的拟合 R² 达 0.93–0.99。经过语言往返后，预设 κ 的排序在四个模型上全部完整还原。显式信念还让 BCA 能暴露各模型的系统性立场偏差，这类偏差在端到端仿真中会被无声吸收。
Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents
LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified, and collective outcomes inherit the model's training prior. We introduce Bayesian Chronicle Agents (BCA), a minimal belief layer separating \emph{what} an agent believes from \emph{how} it speaks. Each stance is a probability, updated by one Bayesian step per utterance heard. A single prior-strength parameter $κ$ encodes stubbornness, modeled after its role in Friedkin--Johnsen (FJ) opinion dynamics. We then sweep this parameter to yield three canonical regimes of opinion dynamics on demand (consensus, persistent disagreement, committed-minority influence), with persistent disagreement matching the FJ closed-form fixed points at $R^2\!=\!0.93$--$0.99$. We further show that prescribed $κ$ remains recoverable after the language round-trip, with perfect rank-order recovery across all four models. Explicit belief also makes simulation auditable: the layer surfaces systematic per-model stance biases that end-to-end simulation would silently absorb.
