发表机构
Mission San Jose High School; University of Chicago（米慎圣何塞高中; 芝加哥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出关系特定的情感精度作为元认知置信度估计，通过调节策略精度而非改变信念内容，在多伙伴信任博弈中区分社会预测与策略承诺。
AI 中文摘要
在多智能体社交环境中，模型可靠性因关系而异。除了推断他人将做什么之外，智能体还必须校准这些推断应如何自信地指导针对每种关系的策略选择。一个智能体可能对某个伙伴维护一个经过充分验证的模型，对另一个伙伴维护一个脆弱的模型，而对第三个伙伴维护一个正在修订的模型；将这些合并为单一的置信度估计会丢失与策略选择相关的信息。因此，我们将情感精度形式化为对当前伙伴模型置信度的关系特定元认知估计。每个伙伴的行为证据更新一个局部置信度估计，该估计在策略选择期间调节策略精度，从而调节当前信念在策略中表达的强度，而不是改变这些信念的内容。在多伙伴分级信任博弈中的模拟表明，伙伴局部情感精度主要通过策略承诺影响行为，而非直接改善伙伴状态推断。由于该机制追踪的是伙伴响应可预测性而非已实现收益，更高的置信度会产生更尖锐的策略承诺，而不一定带来更高的奖励。在社交行为突然转变时，从先前可靠预测中积累的置信度可能在关系改变后仍保持行为活跃，表明置信度修正可能滞后于社会变化。最后，改变精度增益和先验会产生不同的信任校准动态，表明置信度积累和修正依赖于模型参数。综合来看，这些结果展示了关系特定情感精度如何区分社会预测与社会策略承诺。
英文摘要
In multi-agent social settings, model reliability varies across relationships. Beyond inferring what others will do, an agent must calibrate how confidently those inferences should guide policy selection for each relationship. An agent may maintain a well-validated model of one partner, a fragile model of another, and a model under revision for a third; collapsing these into a single confidence estimate loses information relevant to policy selection. We therefore formalize affective precision as a relationship-specific metacognitive estimate of confidence in the current partner model. Each partner's behavioral evidence updates a local confidence estimate that modulates policy precision during selection, regulating how strongly current beliefs are expressed in policy rather than changing the content of those beliefs. Simulations in a multi-partner graded trust game show that partner-local affective precision influences behavior primarily through policy commitment rather than direct improvement of partner-state inference. Because the mechanism tracks partner-response predictability rather than realized payoff, greater confidence produces sharper policy commitment without necessarily producing higher rewards. Under abrupt shifts in social behavior, confidence accumulated from previously reliable predictions can remain behaviorally active after the relationship changes, showing that confidence revision can lag behind social change. Finally, varying precision gain and priors produce distinct trust-calibration dynamics, showing how confidence accumulation and revision depend on model parameters. Together, these results show how relationship-specific affective precision can distinguish social prediction from social policy commitment.
Comments26 pages, 6 figures. Accepted as a full paper at the 7th International Workshop on Active Inference (IWAI 2026). Code: https://github.com/har5h1l/affect_aif
