提出即学习，学习即提出：有限理性下可评估性感知的辅助方法
Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality
浏览论文内容
中文总结 AI 辅助
该研究提出ProSE框架与ProSE-Plan规划器，解决有限理性下AI助手的提案规划问题，通过权衡接受度与可评估性提升辅助效果，优于基线方法。
中文摘要 AI 辅助
AI助手常通过提出候选编辑、计划或设计进行协作，用户在采纳前会对其进行评估。现有辅助方法聚焦于提案质量或用户目标推断，通常假设用户能可靠评估任何提案，但实践中因有限理性会失效。我们研究可评估性感知的提案规划，其中提案兼具任务干预与潜在偏好及评估约束探测的作用，所得信念更新将指导后续提案。我们将该场景形式化为ProSE，这是一个隐参数序列辅助问题，并通过KL正则化的有限理性二元响应模型实例化，其中接受度在价值增益与距离相关的可评估性惩罚间权衡。分析该似然的规划后果发现，可能被接受的提案与信息探测不一定重合，这解释了仅追求接受度的规划者为何系统表现不佳。我们用\textsc{ProSE-Plan}实现ProSE，这是一种深度为2的贝叶斯自适应规划器，通过可能的响应及响应诱导的后验信念对提案评分。在受控图模拟中，当评估成本为瓶颈时，\textsc{ProSE-Plan}相比无感知可评估性及短视基线表现更优，且探测-提交消融实验证实，我们的方法能选择简单方法遗漏的信息性提案。因此，我们的结果表明用户可评估性是AI辅助中与规划相关的维度，可补充生成质量与偏好推断。
英文摘要
AI assistants often collaborate by proposing candidate edits, plans, or designs that users evaluate before adoption. Existing assistance methods focus on proposal quality or user-goal inference, often assuming that the user can reliably evaluate any proposal, which can fail in practice because of bounded rationality. We study evaluability-aware proposal planning, where proposals serve both as task interventions and as probes for learning latent preferences and evaluation constraints, where the resulting belief updates then guide later proposals. We formalise this setting as ProSE, a hidden-parameter sequential assistance problem, and instantiate it with a KL-regularised bounded-rational binary response model in which acceptance trades off value gain against a distance-dependent evaluability penalty. Analysing the planning consequence of this likelihood reveals that likely accepted proposals and informative probes need not coincide, which explains why planners that only pursue acceptance systematically underperform. We operationalise ProSE with \textsc{ProSE-Plan}, a depth-2 Bayes-adaptive planner that scores proposals by possible responses and response-induced posterior beliefs. In controlled graph simulations, \textsc{ProSE-Plan} improves over evaluability-unaware and myopic baselines when evaluation cost is the bottleneck, and a probe-commit ablation confirms that our approach selects informative proposals that simpler methods miss. Our results thus identify user evaluability as a planning-relevant dimension of AI assistance, complementary to generation quality and preference inference.
发表机构
- ELLIS Institute Finland（芬兰ELLIS研究所）
- Aalto University（阿尔托大学）
- University of Manchester（曼彻斯特大学）
机构由 AI 辅助整理，请以论文原文为准。
