Uncovering Why LLMs Fail: From Internal Mechanisms to Adversarial Reasoning Trajectories
arXiv:2610.37369v2 Announce Type: replace Abstract: Large language models (LLMs) are usually evaluated by final-output correctness or safety, yet an endpoint label does not reveal how a failure develops throughout the reasoning process. We therefore ask whether ordinary reasoning failures and adversarially induced failures can be characterized using the same internal coordinates. Towards this end, we in this paper study a white-box diagnostic framework CauTrace to disclose the root-cause of why…