Research map / Large language models / Reasoning and chain of thought
Hidden Patterns in Chain-of-Thought Reasoning
Gregor Bachmann, Yichen Jiang, Seyed-Mohsen Moosavi-Dezfooli, Moin Nabi
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Analyzes chain-of-thought traces to uncover what drives CoT success in LLMs; the abstract is truncated so details beyond the opening motivation are unknown.
Problem
The driving forces behind the success of chain-of-thought prompting in LLMs remain largely unclear.
Approach
An in-depth analysis of CoT traces to identify the underlying factors behind CoT reasoning success; the specific method is not stated in the available text.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Examine per-chunk success probability (potential) of CoT traces on AIME-2024 | non-reasoning and reasoning LLMs · AIME-2024 | fraction of monotonic potential curves: 15% to 45% monotonic across models | Mixed |
| Flag late-spike (guess) samples when computing pass@k | Qwen2.5-1.5B and 7B · AIME-2025 | pass@k | Hurt |
| Greedily select the highest-potential candidate chunk at each step (optimized CoT) | Qwen2.5-1.5B · AIME-2025 | potential monotonicity | Improved |
| Provide 20% of a stronger model's partial CoT to Qwen3-0.6B | Qwen3-0.6B · AIME-2025 | accuracy | Improved |
| Provide partial CoT from GPT-OSS-20B instead of same-family Qwen3-32B | Qwen3-0.6B · AIME-2025 | accuracy | Mixed |
| Provide partial summary CoT from Qwen3-235B to non-reasoning models | Qwen2.5-7B and Qwen2.5-72B · AIME-2024 | accuracy | Improved |
| Use reasoning models (Qwen3) rather than non-reasoning models | AIME-2024 CoT traces · AIME-2024 | % CoTs with tangent: Qwen3-0.6B 41% vs Qwen2.5-1.5B 5% | Hurt |
Closest papers by meaning
- Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns (AAAI 2025 · similarity 0.93)
- Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought (NeurIPS 2024 · similarity 0.92)
- Chain-of-Thought Reasoning In The Wild Is Not Always Faithful (ICML 2026 · similarity 0.92)
- To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning (ICLR 2025 · similarity 0.92)
- Chain of Thoughtlessness? An Analysis of CoT in Planning (NeurIPS 2024 · similarity 0.92)
- Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning (NeurIPS 2025 · similarity 0.91)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
