arXiv AI
Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 22
The Stepwise Informativeness Assumption: When Do Entropy Dynamics Track Reasoning Correctness in LLMs?
arXiv:2604.06192v2 Announce Type: replace-cross Abstract: Recent work uses entropy-based signals at multiple representation levels to study reasoning in large language models, but the field remains l...
arXiv Computation and Language
5d ago
Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics
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.
arXiv AI
Oct 2
Interpreting Reasoning of Large Language Models via Partial Information Decomposition
arXiv:2610.00571v1 Announce Type: cross Abstract: Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive,...
arXiv Computation and Language
Oct 27
STEP: Soft Trajectory Estimation of Prediction Correctness via Per-Step Probability Scoring
arXiv:2610.34537v1 Announce Type: new Abstract: Estimating the correctness of large language model (LLM) predictions without access to ground truth is critical for reliable deployment in high-stakes...
arXiv Machine Learning
Aug 11
Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond
arXiv:2510. 19990v2 Announce Type: replace Abstract: The reasoning paradigm, where language models reason before answering, has enabled breakthroughs on tasks such as mathematical problem-solving.
arXiv AI
Jun 12
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
arXiv:2606. 13603v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individual steps on the final answer poorly understood.