Doesn't Stop Reasoning: Analysis of Spurious CoT Termination

• URL: http://arxiv.org/abs/2609.03633v1
• Date: Thu, 03 Sep 2026 10:25:23 GMT
• Title: </think> Doesn't Stop Reasoning: Analysis of Spurious CoT Termination
• Abstract summary: We study a strategy that injects an end-of-think token (EoT) at this point to trigger the reasoning-to-answering transition.<n>We find that the injected EoT does not always induce a clean answering phase.<n>We call this spurious CoT termination, where reasoning-like generation continues into the answering phase.
• Score: 8.097661521171581
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chain-of-thought (CoT) reasoning improves large reasoning models (LRMs) on complex tasks but often produces long, redundant traces. Recent training-free early-exit methods shorten these traces by choosing an intermediate point to stop reasoning. We study one such strategy that injects an end-of-think token (EoT, </think>) at this point to trigger the reasoning-to-answering transition, and find that the injected EoT does not always induce a clean answering phase. Answering-phase generation can continue before the model regenerates another EoT, with the span preceding this regenerated EoT scaling with the reasoning tokens saved by early exit and exhibiting continued reasoning behavior. We call this spurious CoT termination, where reasoning-like generation continues into the answering phase. We hypothesize that insufficient attention to the injected EoT contributes to spurious CoT termination and probe this hypothesis with Exit-token Attention Biasing (EAB). Across four LRMs, five benchmarks, and two early-exit methods, increasing attention to the injected EoT reduces spurious CoT termination and answering-phase length. These results reveal a limitation of controlling LRMs by externally matching their explicit think-block format. Inserting the EoT token conforms to this format but does not by itself guarantee the intended reasoning-to-answering transition. Our code is available at https://github.com/Seunghee-Koh/Spurious-CoT-Termination.

Related papers

• WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models [51.88075626243057]
  We propose WhisperRec, an efficient latent reasoning framework for foundation recommendation models (FRMs)<n>WhisperRec compresses teacher-generated Chain-of-Thought (CoT) into learnable latent reasoning tokens.<n>We show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines.
  arXiv  Detail & Related papers  (2026-07-29T08:48:35Z)
• ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning [69.64972562984882]
  We propose ThoughtFold, a framework that leverages fine-grained preference learning to redundant explorations for efficient reasoning.<n>We show that ThoughtFold significantly enhances efficiency.<n>It reduces the token usage of DeepSeek-R1-Distill-Qwen-7B by approximately 56% while maintaining state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2026-06-02T11:21:27Z)
• Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models [17.588873255093596]
  Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT)<n>LRMs often overthink, continuing to reason after a solution has already stabilized and thereby wasting tokens and increasing latency.<n>We propose PUMA, a plug-and-play framework that combines a lightweight Redundancy Detector with answer-level verification.
  arXiv  Detail & Related papers  (2026-05-17T22:04:11Z)
• Chain Of Thought Compression: A Theoritical Analysis [24.613200477865572]
  Chain-of-Thought (CoT) has unlocked advanced reasoning abilities of Large Language Models.<n>CoT incurs prohibitive computational costs due to generation of extra tokens.<n>Recent studies show that compressing reasoning steps into latent states, or implicit CoT compression, offers a token-efficient alternative.
  arXiv  Detail & Related papers  (2026-01-29T11:42:03Z)
• Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization [9.193078163792427]
  Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems.<n>Recent latent reasoning approaches attempt to optimize efficiency by performing reasoning within continuous hidden states.<n>We introduce PLaT, a framework that reformulates latent reasoning as planning by fundamentally decouple reasoning from verbalization.
  arXiv  Detail & Related papers  (2026-01-29T07:38:18Z)
• One Token Embedding Is Enough to Deadlock Your Large Reasoning Model [91.48868589442837]
  We present the Deadlock Attack, a resource exhaustion method that hijacks an LRM's generative control flow.<n>Our method achieves a 100% attack success rate across four advanced LRMs.
  arXiv  Detail & Related papers  (2025-10-12T07:42:57Z)
• Stop Spinning Wheels: Mitigating LLM Overthinking via Mining Patterns for Early Reasoning Exit [114.83867400179354]
  Overthinking can degrade overall performance of large language models.<n>We categorize reasoning into three stages: insufficient exploration stage, compensatory reasoning stage, and reasoning convergence stage.<n>We develop a lightweight thresholding strategy based on rules to improve reasoning accuracy.
  arXiv  Detail & Related papers  (2025-08-25T03:17:17Z)
• ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy [8.962703809086628]
  ThinkLess is an inference-efficient framework that terminates reasoning generation early and maintains output quality without modifying the model.<n>We show that ThinkLess achieves comparable accuracy to full-length Chain-of-Thought (CoT) decoding while greatly reducing decoding time and memory consumption.
  arXiv  Detail & Related papers  (2025-05-21T15:58:16Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering [59.495717939664246]
  Large language models have manifested remarkable capabilities by leveraging chain-of-thought (CoT) reasoning techniques to solve intricate questions. We propose a novel approach called the selective filtering reasoner (SelF-Reasoner) that assesses the entailment relationship between the question and the candidate reasoning chain. SelF-Reasoner improves the fine-tuned T5 baseline consistently over the ScienceQA, ECQA, and LastLetter tasks.
  arXiv  Detail & Related papers  (2024-03-28T06:28:35Z)

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.