arXiv AI
Jun 11
Forecasting Future Behavior as a Learning Task
arXiv:2606. 11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs.
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.
Related stories
arXiv Machine Learning
Jun 10
Predicting Future Behaviors in Reasoning Models Enables Better Steering
arXiv:2606. 11172v1 Announce Type: new Abstract: Deployed large reasoning models (LRMs) often behave unexpectedly.
arXiv AI
Jul 24
Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
arXiv AI
Sep 10
Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
arXiv:2609.09030v1 Announce Type: new Abstract: Chain-of-thought reasoning provides a structured computation between a model's input and final answer. Yet it is often evaluated through endpoint accur...
arXiv AI
Jul 24
Diagnosing Pathological Chain-of-Thought in Reasoning Models
arXiv:2602. 13904v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety.
arXiv AI
Sep 16
State of Thought Enables Endogenous Reasoning
arXiv:2609.16055v1 Announce Type: cross Abstract: Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasonin...
arXiv AI
Jul 24
Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought Models
arXiv:2607. 21433v1 Announce Type: cross Abstract: Chain-of-thought reasoning models such as DeepSeek-R1-Distill-Qwen-7B exhibit a bimodal convergence pattern: generations either terminate within a token budget (converged) or exhaust it without reaching a conclusion (non-converged).
arXiv AI
Jul 10
What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness
arXiv:2607. 08046v1 Announce Type: cross Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast.
arXiv AI
Aug 17
Early Stopping for Large Reasoning Models via Confidence Dynamics
arXiv:2604. 04930v2 Announce Type: replace-cross Abstract: Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking.
arXiv AI
Jun 16
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
arXiv:2605. 22873v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial?
arXiv AI
Aug 5
Evading Chain-of-Thought Monitoring Through Model Poisoning
arXiv:2608. 02820v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions.
arXiv AI
Jul 21
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
arXiv:2607. 18100v1 Announce Type: new Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable.