Me, Myself, and $\pi$ : Evaluating and Explaining LLM Introspection

Computer Science > Artificial Intelligence [Submitted on 17 Mar 2026] Me, Myself, and π : Evaluating and Explaining LLM Introspection Atharv Naphade, Samarth Bhargav, Sean Lim, Mcnair Shah A hallmark of human intelligence is Introspection-the ability to assess and reason about one's own cognitive processes. Introspection has emerged as a promising but contested capability in large language models (LLMs). However, current evaluations often fail to distinguish genuine meta-cognition from the mere application of general world knowledge or text-based self-simulation. In this work, we propose a principled taxonomy that formalizes introspection as the latent computation of specific operators over a model's policy and parameters. To isolate the components of generalized introspection, we present Introspect-Bench, a multifaceted evaluation suite designed for rigorous capability testing. Our results show that frontier models exhibit privileged access to their own policies, outperforming peer models in predicting their own behavior. Furthermore, we provide causal, mechanistic evidence explaining both how LLMs learn to introspect without explicit training, and how the mechanism of introspection emerges via attention diffusion. Comments: 20 pages, 12 figures, ICLR 2026 Workshop: From Human Cognition to AI Reasoning: Models, Methods, and Applications Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.20276 [cs.AI]   (or arXiv:2603.20276v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.20276 Focus to learn more Submission history From: Atharv Naphade [view email] [v1] Tue, 17 Mar 2026 17:39:25 UTC (8,932 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)