arXiv：cs.AI（全量分类）· Yizhi Liu, Balaji Padmanabhan, Siva Viswanathan·· 5 小时前AI 评分27
论文提出 LLM 智能体的认知行动框架：决策前如何准备证据
Before Agents Decide: Epistemic Action in LLM-Based Systems
AI 导读
一篇被 NeurIPS 2026 FAST Workshop 接收的论文将认知科学中的"认知行动"概念引入 LLM 智能体，区分出三种模式：获取缺失证据、转换已有证据、探测系统以生成有揭示性的响应。作者用"认知脚手架"指代使这些行动成为可能的接口、工具与环境，并主张智能体设计必须解决"决策就绪证据"如何产生的问题。
正文
Abstract:Before a difficult decision, people often act simply to understand the situation better. We turn an object to see another side, place alternatives next to each other, or change one condition and observe what happens. These actions may not complete the task, but they improve the evidence needed for the next choice. LLM-based agents can search and explore, yet agent design gives less attention to an earlier question: is the available evidence ready for the decision? Sometimes necessary evidence is missing. In other cases, the evidence is present but its form hides what matters, or the comparison needed to judge it does not yet exist. Cognitive science calls actions that improve the basis for a later choice epistemic actions. We bring this idea to LLM-based agents and distinguish three modes: acquiring missing evidence, transforming available evidence, and probing a system to create a revealing response. We use the term epistemic scaffolding for the interfaces, tools, and environments that make these actions possible and auditable. This paper argues that agent design must address how decision-ready evidence is produced.
| Comments: | Accepted at the Foundations of Agentic Systems Theory (FAST) Workshop at NeurIPS 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.00511 [cs.AI] |
| (or arXiv:2610.00511v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00511 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yizhi Liu [view email]
[v1]
Wed, 30 Sep 2026 18:07:41 UTC (1,378 KB)
来源：arXiv：cs.AI（全量分类） · arxiv.org