</think> Doesn't Stop Reasoning: Analysis of Spurious CoT Termination

2026-09-03

AI Summary

研究解决链式思维推理中的冗长问题，通过提前退出方法并分析其不足，提出增加对终止标记的关注以减少错误终止和回答阶段长度。

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.

Problem

• Chain-of-thought
• Early-exit
• Spurious CoT termination
• End-of-think token

Innovation

• Chain-of-thought (CoT) reasoning
• End-of-think token (EoT)
• Spurious CoT termination
• Exit-token Attention Biasing (EAB)