Honest Lying: Understanding Memory Confabulation in Reflexive Agents

ArXi:2605.29463v1 Announce Type: cross Reflexion-style agents rely on self-generated reflections as memory, implicitly assuming that agents can accurately diagnose their own failures. We show that this assumption can fail systematically: across ALFWorld and HumanEval, agents confident but incorrect interpretations of the task and continue acting on them across trials,even though the environment resets to the correct task each time. We call this failure mode memory confabulation and.