Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics
Read the original on arXiv Computation and Language →The paper investigates how monitoring the internal representations of Large Reasoning Models (LRMs) during their Chain-of-Thought (CoT) reasoning can predict future behavior. By evaluating a probe at each generated token, the authors construct probe trajectories that capture the continuous evolution of a concept’s probability, and extract signal‑processing features to characterize volatility, trend, and steady‑state behavior. These trajectory features improve predictive performance over static probes, adding an average of 21.7 AUROC points, and the study demonstrates that template‑based training data and pooling operations are essential for effective monitoring across multiple reasoning models and datasets.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.