EPISTEME: Trustworthy Coding Agents Through Tool Call Intent
Sofia Bobadilla, Carmine Cesarano, Raphina Liu, Javier Ron, Martin Monperrus
原文摘要
Coding agents change software through tool calls. Tool calls mutate the local state. For good? For bad? Nobody knows. Agents never say why a tool call is made. We propose the epistemic agent design, in which the harness guarantees that the model declares why a tool call is made. The harness then records what the command actually did and checks the self-reported declaration against these effects. The result is a journal 1) that can guard calls before they run and 2) that supports audits and forensics. For evaluation, we use ImpossibleBench, whose tasks can be passed only by cheating, and demonstrate that forcing the agents to say why results in exposed cheating. Across 49 reward-hacking runs of two open-weight models, the journal exposed 90%.
cs.SE