When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel

• URL: http://arxiv.org/abs/2605.11746v1
• Date: Tue, 12 May 2026 08:24:47 GMT
• Title: When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
• Abstract summary: Chain-of-thought (CoT) traces are increasingly used to improve language model capability and to audit model behavior.<n>We test this assumption with a step-level Detect-Classify-Compare framework built around an answer-commitment proxy.<n>Across nine models and seven reasoning benchmarks, latent commitment and explicit answer arrival align on only 61.9% of steps on average.
• Score: 5.106950500256654
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We test this assumption with a step-level Detect-Classify-Compare framework built around an answer-commitment proxy that is cross-validated with Patchscopes, tuned-lens probes, and causal direction ablation. Across nine models and seven reasoning benchmarks, latent commitment and explicit answer arrival align on only 61.9% of steps on average. The dominant mismatch pattern is confabulated continuation: 58.0% of detected mismatch events occur after the answer-commitment proxy has already stabilized while the trace continues producing deliberative-looking text, and a vacuousness analysis shows that the committed answer does not change during these steps. In architecture-matched Qwen2.5/DeepSeek-R1-Distill comparisons, the reasoning pipeline changes failure composition more than aggregate alignment, most clearly at 32B where confabulated steps decrease as contradictory states increase. Lower step-level alignment is also associated with larger CoT utility, suggesting that the settings that benefit most from CoT are often the least temporally faithful. Paired truncation and a complementary donor-corruption test further indicate that much post-commitment text is not load-bearing for the final answer. These findings suggest that CoT can remain useful while still being an unreliable report of when the answer was formed.

Related papers

• One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control [62.82372407840088]
  We show that same-point domain gradients may remain nearly even when consecutive realized updates partially reverse one another in output space.<n>We propose OSOL, which designates a focus domain at each iteration, to rank token-level rebound risk.<n>OSOL reaches a domain-macro average of 0.4822, improving by 5.7% over the strongest compared baseline, without explicit higher-order differentiation.
  arXiv  Detail & Related papers  (2026-09-06T08:32:59Z)
• Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents [60.650808962786364]
  We study whether native MoE router traces can guide steering and selection without an external judge or selection-time test execution.<n>Our analysis shows that routing provides a robust behavioral role signal; token-granular readouts and decision-matched comparison sets turn it into effective control.<n>We evaluate on SWE-bench Verified using open-weight sparse MoE agents across scales and reasoning-effort settings.
  arXiv  Detail & Related papers  (2026-08-23T03:07:03Z)
• Cross-View Correspondence Is a Measurement Intervention: Two-Sided Validation for Agent Evaluation and Credit Assignment [3.2479665905442645]
  Cross-view correspondence must be declared, validated, and propagated into uncertainty before agent evaluation or credit assignment supports a point conclusion.<n>We develop a validity theory and audit with three components: two-sided validation of nuisance removal and response preservation, all-optima identification of downstream conclusions, and uncertainty propagation after validity is established.
  arXiv  Detail & Related papers  (2026-08-18T12:39:21Z)
• The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics [0.9668407688201359]
  Chain-of-thought (CoT) reasoning improves large language model (LLM) performance.<n>Existing approaches that leverage verbalized CoTs to monitor reasoning correctness largely evaluate the semantic correctness or consistency of individual intermediate steps.<n>We show that capability failures can manifest as distributed, task-dependent changes in the structure of visible reasoning.
  arXiv  Detail & Related papers  (2026-08-04T08:04:36Z)
• GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning [61.67411833252235]
  We introduce GradCuit, which inserts optimizable latent states at a selected Transformer layer between the hidden representations of the prompt and the generated continuation.<n>Across five instruction-tuned backbones, three reasoning benchmarks, and two answer formats, GradCuit achieves an average accuracy of 64.5%.<n>For interpretability, token-level gradient attribution reveals that latent influence concentrates on reasoning-connector tokens, while layer analysis identifies early-to-middle Transformer layers as the most effective optimization space.
  arXiv  Detail & Related papers  (2026-08-03T17:55:24Z)
• TrAC: Trace-Conditioned Answer Consistency for Efficient Uncertainty Quantification in LLMs [5.676157325165344]
  Large language models (LLMs) can generate fluent reasoning traces that nevertheless lead to incorrect answers.<n>TrAC is a correctness-supervised uncertainty quantification framework that combines active and passive signals anchored to one completed reasoning trace.<n>TrAC improves macro AUROC by 1.8% and reduces AURC by 3.4% relative to eight-sample self-consistency.
  arXiv  Detail & Related papers  (2026-08-01T03:43:31Z)
• Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong [1.2744523252873352]
  Black-box (behavioral) detection of unfaithful CoT against FaithCoT-Bench's human annotations.<n>We find answer correctness structures the problem at every level.
  arXiv  Detail & Related papers  (2026-07-26T04:43:53Z)
• Closing the Loop on Latent Reasoning via Test-Time Reconstruction [45.08180971427891]
  Recent work moves intermediate reasoning from natural-language traces into latent or cache-level representations.<n>We propose ReLAT, a self-supervised test-time training method that closes this loop using the query itself as the reference.<n>We show that ReLAT consistently improves over single-model inference, text-based collaboration, open-loop latent collaboration, and alternative test-time training objectives.
  arXiv  Detail & Related papers  (2026-06-04T14:54:40Z)
• Beyond the Attention Stability Boundary: Agentic Self-Synthesizing Reasoning Protocols [6.357772907811544]
  Self- Synthesizing Reasoning Protocols (SSRP) is a metacognitive framework that implements a discrete separation between architectural planning and procedural execution.<n>We present 3 experimental tiers: a shallow recency-based retrieval pilot, a high-entropy SOP, and a semantic hijacked 3-hop Multi-Fact Synthesis task.<n>Our results empirically locate the Attention Stability Boundary, where stateless Vanilla ReAct baselines for GPT 5.4 collapse to 0.1% success while SSRP achieves a 715X Resilience Lift.
  arXiv  Detail & Related papers  (2026-04-27T14:13:30Z)
• 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)
• SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio [0.038379177968040606]
  We propose SELFDOUBT, a single-pass uncertainty framework for reasoning language models.<n>Our key signal, the Hedge-to-Verify Ratio (HVR), detects whether a reasoning trace contains uncertainty markers and, if so, whether they are offset by explicit selfchecking behavior.<n> SELFDOUBT operates on a single observed reasoning trajectory, making it suitable for latency- and cost-constrained deployment over any proprietary API.
  arXiv  Detail & Related papers  (2026-04-07T19:19:29Z)
• Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval [0.0]
  Large Language Models (LLMs) have achieved unprecedented fluency but remain susceptible to "hallucinations"<n>We propose a tiered retrieval and verification architecture designed to intercept factual inaccuracies by shifting LLMs from pattern-matchers to verified truth-seekers.<n>System was evaluated across 650 queries from five diverse benchmarks.
  arXiv  Detail & Related papers  (2026-03-18T15:59:30Z)
• Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning [66.22060690012512]
  Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy.<n>We propose Step-wise Adaptive Penalization (SWAP), a fine-grained framework that allocates length reduction across steps based on intrinsic contribution.
  arXiv  Detail & Related papers  (2026-02-27T20:23:59Z)
• CORE: Context-Robust Remasking for Diffusion Language Models [51.59514489363897]
  We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision.<n>Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations.<n>On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.
  arXiv  Detail & Related papers  (2026-02-04T00:12:30Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models [14.840508854268522]
  Reasoning language models improve performance on complex tasks by generating long chains of thought (CoTs)<n>We evaluate a range of monitoring methods using either CoT text or activations.<n>We find that a simple linear probe trained on CoT activations significantly outperforms all text-based baselines in predicting whether a final response is safe or unsafe.
  arXiv  Detail & Related papers  (2025-07-16T17:16:03Z)

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.