mlsanityData to 14 Oct 2026

EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation

arXiv 2601.03769 ↗First posted 7 Jan 2026cs.AIcited by 1

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Chain-of-Thought (CoT) prompting has significantly enhanced the mathematical reasoning capabilities of Large Language Models. We find existing fine-tuning datasets frequently suffer from the "answer right but reasoning wrong" probelm, where correct final answers are derived from hallucinated, redundant, or logically invalid intermediate steps. This paper proposes EntroCoT, a unified framework for automatically identifying and refining low-quality CoT supervision traces. EntroCoT first proposes an entropy-based mechanism to segment the reasoning trace into multiple steps at uncertain junctures, and then introduces a Monte Carlo rollout-based mechanism to evaluate the marginal contribution of each step. By accurately filtering deceptive reasoning samples, EntroCoT constructs a high-quality dataset where every intermediate step in each reasoning trace facilitates the final answer. Extensive experiments on mathematical benchmarks demonstrate that fine-tuning on the subset constructed by EntroCoT consistently outperforms the baseslines of full-dataset supervision.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 8 of its 8 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

8 of 8 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search22 May

Other references · 7

  1. 2023Let's Verify Step by Stepcited by 3,789
  2. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  3. 2025The Lessons of Developing Process Reward Models in Mathematical Reasoningcited by 415
  4. 2023Evaluating the Performance of Large Language Models on GAOKAO Benchmarkcited by 186
  5. 2025Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thoughtcited by 109
  6. 2024MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Datacited by 52
  7. 2025Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillationcited by 43

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models
  2. 2025Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
  3. 2026EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning Models
  4. 2025Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning
  5. 2026Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning
  6. 2026Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
  7. 2026DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs
  8. 2026ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning