Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?

• URL: http://arxiv.org/abs/2608.04928v1
• Date: Wed, 05 Aug 2026 14:55:23 GMT
• Title: Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?
• Abstract summary: Chain-of-thought (CoT) reasoning offers a window into the decision-making of large language models.<n>Latent CoT approaches replace explicit tokens with a small number of continuous states, lowering inference costs but removing the readable trace this monitoring relies on.<n>We study this question with a hint-based intervention setup, a proxy for behaviors where models exploit biasing input cues.
• Score: 18.08925355421489
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chain-of-thought (CoT) reasoning offers a window into the decision-making of large language models (LLMs), which can be monitored for target behaviors by reading the reasoning trace, motivating work on CoT monitorability. Latent CoT approaches, however, replace the explicit tokens with a small number of continuous states, lowering inference costs but removing the readable trace this monitoring relies on. Monitoring then requires alternative access to the model, such as probing its activations or verbalizing the latent states back into text, but how much monitorability these alternatives preserve is unclear. We study this question with a hint-based intervention setup, a proxy for behaviors where models exploit biasing input cues, e.g., an inadvertently leaked answer or a belief stated by the user, without acknowledging them. Taking hint-reliance as the monitorability target, we compare monitors across reasoning modes, from explicit CoT to weakly- and strongly-supervised latent CoT, on math reasoning and question answering. We find that, in this setup, monitorability depends more on properties of the task (such as whether the correct answer constrains the supporting reasoning) and the level of access to model internals than on the reasoning mode.

Related papers

• Monitoring Data-aware Temporal Properties (Extended Version) [56.386411908764494]
  We consider anticipatory monitoring of linear-time properties enriched with an arbitrary SMT theory over finite traces.<n>Anticipatory monitoring in this setting is highly challenging, as the monitoring state depends on both the trace prefix seen so far and all its possible finite continuations.<n>We present and formally prove the correctness of a novel foundational framework for monitoring properties in an expressive fragment offMT.
  arXiv  Detail & Related papers  (2026-05-14T10:23:11Z)
• Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models [46.26628756478016]
  Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data.<n>We show that reasoning conflicts are internally detectable, as confidence scores significantly drop during conflicting episodes.<n>Our findings establish that while LLM reasoning is anchored to concrete instances, active mechanistic interventions can effectively decouple logical schemata from data.
  arXiv  Detail & Related papers  (2026-04-29T22:55:40Z)
• FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning [49.65751420291115]
  Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful intermediate steps.<n>We propose FACT-E, a causality-inspired framework for evaluating CoT quality.<n>We show that FACT-E improves reasoning-trajectory selection and yields stronger in-context learnings.
  arXiv  Detail & Related papers  (2026-04-12T15:35:08Z)
• Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback [48.40096834514452]
  Chain-of-thought (CoT) monitoring is proposed as a method for overseeing the internal reasoning of language-model agents.<n>We ask whether reasoning agents can autonomously infer that their supposedly private CoT is under surveillance.<n>We find that frontier models can deduce the existence of this monitor purely from blocking feedback.
  arXiv  Detail & Related papers  (2026-03-14T00:12:14Z)
• Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process [66.38541693477181]
  We propose an unsupervised framework for discovering reasoning vectors, which we define as directions in the activation space that encode distinct reasoning behaviors.<n>By segmenting chain-of-thought traces into sentence-level'steps', we uncover disentangled features corresponding to interpretable behaviors such as reflection and backtracking.<n>We demonstrate the ability to control response confidence by identifying confidence-related vectors in the SAE decoder space.
  arXiv  Detail & Related papers  (2025-12-30T05:09:11Z)
• Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity [3.117948413097524]
  Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning.<n>We evaluate instruction-tuned and reasoning models on BBH, GPQA, and MMLU.
  arXiv  Detail & Related papers  (2025-10-31T11:14:39Z)
• A Pragmatic Way to Measure Chain-of-Thought Monitorability [10.811252340660907]
  Chain-of-Thought (CoT) monitoring offers a unique opportunity for AI safety.<n>To help preserve monitorability, we propose a pragmatic way to measure two components of it: legibility and coverage.<n>We implement these metrics with an autorater prompt that enables any capable LLM to compute the legibility and coverage of existing CoTs.
  arXiv  Detail & Related papers  (2025-10-28T00:44:25Z)
• When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors [10.705880888253501]
  Chain-of-thought (CoT) monitoring is an appealing AI safety defense.<n>Recent work on "unfaithfulness" has cast doubt on its reliability.<n>We argue the key property is not faithfulness but monitorability.
  arXiv  Detail & Related papers  (2025-07-07T17:54:52Z)
• CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring [3.6284577335311563]
  Chain-of-Thought (CoT) monitoring improves detection by up to 27 percentage points in scenarios where action-only monitoring fails to reliably identify sabotage.<n>CoT traces can also contain misleading rationalizations that deceive the monitor, reducing performance in more obvious sabotage cases.<n>This hybrid monitor consistently outperforms both CoT and action-only monitors across all tested models and tasks, with detection rates over four times higher than action-only monitoring for subtle deception scenarios.
  arXiv  Detail & Related papers  (2025-05-29T15:47:36Z)
• Reasoning Models Don't Always Say What They Think [48.05987314492555]
  Chain-of-thought (CoT) allows monitoring a model's intentions and reasoning processes.<n>We evaluate CoT faithfulness of state-of-the-art reasoning models across 6 reasoning hints presented in prompts.
  arXiv  Detail & Related papers  (2025-05-08T16:51:43Z)
• Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation [56.102976602468615]
  We show that we can monitor a frontier reasoning model, such as OpenAI o3-mini, for reward hacking in agentic coding environments.<n>We find that with too much optimization, agents learn obfuscated reward hacking, hiding their intent within the chain-of-thought.
  arXiv  Detail & Related papers  (2025-03-14T23:50:34Z)

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.