🤖 AI Summary
This study addresses the challenges of insufficient pre-decision evidence, opaque cognitive processes, and the absence of comparative benchmarks in large language model (LLM) agents. To this end, it pioneers the integration of the "cognitive action" theory from cognitive science into agent design. By establishing three cognitive modes—acquisition, transformation, and probing—this work proposes an auditable cognitive scaffolding framework augmented with toolchain interfaces to optimize pre-decision evidence preparation. The research develops a systematic mechanism for producing decision-ready evidence, thereby significantly enhancing both the reasoning reliability and interpretability of LLM agents in complex tasks.
📝 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.