</think> Doesn't Stop Reasoning: Analysis of Spurious CoT Termination
On the map: LLM reasoning → Prompting and chain-of-thought reasoning
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 13 of its 56 references that are in the map. First posted on arXiv 3 Sep 2026.
Builds on
13 of 56 references.
Closest ancestors · 3
Same direction, newest first
- 2025Thought Anchors: Which LLM Reasoning Steps Matter?23 Jun
- 2025Chain of Draft: Thinking Faster by Writing Less25 Feb
- 2024Distilling System 2 into System 18 Jul
Other references · 10
- 2021Training Verifiers to Solve Math Word Problemscited by 10,109
- 2025Qwen3 Technical Reportcited by 8,820
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
- 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 464
- 2025How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approachcited by 97
- 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Modelscited by 36
- 2025Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Trainingcited by 8
- 2025When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoningcited by 7
- 2026Gradient-Stable Attention Heads Signal LLM Correctnesscited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
- 2025Early Stopping Chain-of-thoughts in Large Language Models
- 2026Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
- 2026Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation Patching
- 2025Dynamic Early Exit in Reasoning Models
- 2026SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation
- 2024How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning
- 2026When Chain-of-Thought Fails, the Solution Hides in the Hidden States