Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resolution Profiles

arXiv:2605.27784v1 Announce Type: new Abstract: LLM agents are governed by long-lived natural-language prompt policies, but individually reasonable standing rules can interact in uninspected ways. We study live intra-policy rule-conflict diagnosis: finding rule pairs inside a single prompt policy that can co-govern a realistic state, and measuring how models resolve that pressure in responses or tool actions. We introduce WIRE, a Witnessed Intra-policy Rule Evaluation pipeline. WIRE extracts so