Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics

• URL: http://arxiv.org/abs/2605.18549v1
• Date: Mon, 18 May 2026 15:29:04 GMT
• Title: Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics
• Abstract summary: Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning.<n>We investigate the hidden representations of LRMs to determine whether future behavior can be predicted from prompt and CoT representations.<n>We find that future model behavior is more distinguishable when examined over the full trajectory than from a single static prediction.
• Score: 42.27928681606673
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not always faithful to the model's final output, undermining its reliability as a monitoring tool. To address this, we investigate the hidden representations of LRMs to determine whether future behavior can be predicted from prompt and CoT representations. By evaluating a probe at each generated token, we construct a probe trajectory, the continuous evolution of a concept's probability across the reasoning process. We find that future model behavior is more distinguishable when examined over the full trajectory than from a single static prediction. To characterize these temporal dynamics, we extract signal-processing features that capture volatility, trend, and steady-state behavior, significantly improving the separation of future model states. We also present two methodological insights. First, template-based training data achieves near-parity with dynamically generated model responses, eliminating the need for a costly initial inference and labeling. Second, the choice of pooling operation is critical: average-pooling and last-token methods collapse to near-random performance, while max-pooling achieves up to 95% AUROC and yields stable probe trajectories. Using four datasets and four reasoning models across the domains of safety and mathematics, we demonstrate that trajectory features encode task-specific dynamics that improve outcome separability. These findings establish probe trajectories as a complementary framework for monitoring LRM behavior. Warning: This article contains potentially harmful content.

Related papers

• Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models [28.165928090888986]
  World Action Models (WAMs) enable decision-making through imagined rollouts by predicting future observations and actions.<n>We identify action-state consistency, the alignment between predicted actions and induced state transitions, as a missing reliability axis for WAMs.<n>We introduce a value-free consensus strategy for test-time selection, which ranks candidate rollouts by agreement among predicted futures.
  arXiv  Detail & Related papers  (2026-05-08T09:44:43Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making [48.998030470623384]
  offline decision-making requires reliable behaviors from fixed datasets without further interaction.<n>We propose a compositional model-based diffusion framework consisting of: (i) a planner that generates diverse, task-aligned trajectories; (ii) a dynamics model that enforces consistency with the underlying system dynamics; and (iii) a ranker module that selects behaviors aligned with the task objectives.
  arXiv  Detail & Related papers  (2025-12-09T06:26:02Z)
• Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines [8.895768051554162]
  We propose a novel generative pre-training paradigm for e-commerce recommender systems.<n>Our model learns to predict the Next Interest Flow, a dense vector sequence representing a user's future intent.<n>We present the All-domain Moveline Evolution Network (AMEN), a unified framework implementing our entire pipeline.
  arXiv  Detail & Related papers  (2025-10-13T12:13:17Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Parallel Test-Time Scaling for Latent Reasoning Models [58.428340345068214]
  Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs)<n>Recent advances in latent reasoning, where intermediate reasoning unfolds in continuous vector spaces, offer a more efficient alternative to explicit Chain-of-Thought.<n>This work enables parallel TTS for latent reasoning models by addressing the above issues.
  arXiv  Detail & Related papers  (2025-10-09T03:33:00Z)
• Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Prediction [10.21659221112514]
  We introduce a novel trajectory prediction framework that leverages causal inference to enhance predictive robustness, generalization, and accuracy.<n>Our findings highlight the potential of causal reasoning to transform trajectory prediction, paving the way for robust autonomous driving systems.
  arXiv  Detail & Related papers  (2025-05-11T05:56:07Z)
• FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation [15.64941169350615]
  Data assimilation (DA) integrates observations with a dynamical model to estimate states of PDE-governed systems.<n>FlowDAS is a generative DA framework that uses interpolants to learn state transition dynamics.<n>We show that FlowDAS surpasses model-driven methods, neural operators, and score-based baselines in accuracy and physical plausibility.
  arXiv  Detail & Related papers  (2025-01-13T05:03:41Z)
• Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior [51.60683890503293]
  We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. We show that pure supervised cloning can generate trajectories matching the per-time step distribution of arbitrary expert trajectories.
  arXiv  Detail & Related papers  (2023-07-27T04:27:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.