The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917198141849600 |
|---|---|
| author | Chen, Qiguang Du, Yantao Li, Ziniu Liu, Jinhao Duan, Songyao Guo, Jiarui Liu, Minghao Liu, Jiaheng Yang, Tong Zhang, Ge Qin, Libo Che, Wanxiang Huang, Wenhao |
| author_facet | Chen, Qiguang Du, Yantao Li, Ziniu Liu, Jinhao Duan, Songyao Guo, Jiarui Liu, Minghao Liu, Jiaheng Yang, Tong Zhang, Ge Qin, Libo Che, Wanxiang Huang, Wenhao |
| contents | Large language models (LLMs) often fail to learn effective long chain-of-thought (Long CoT) reasoning from human or non-Long-CoT LLMs imitation. To understand this, we propose that effective and learnable Long CoT trajectories feature stable molecular-like structures in unified view, which are formed by three interaction types: Deep-Reasoning (covalent-like), Self-Reflection (hydrogen-bond-like), and Self-Exploration (van der Waals-like). Analysis of distilled trajectories reveals these structures emerge from Long CoT fine-tuning, not keyword imitation. We introduce Effective Semantic Isomers and show that only bonds promoting fast entropy convergence support stable Long CoT learning, while structural competition impairs training. Drawing on these findings, we present Mole-Syn, a distribution-transfer-graph method that guides synthesis of effective Long CoT structures, boosting performance and RL stability across benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06002 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning Chen, Qiguang Du, Yantao Li, Ziniu Liu, Jinhao Duan, Songyao Guo, Jiarui Liu, Minghao Liu, Jiaheng Yang, Tong Zhang, Ge Qin, Libo Che, Wanxiang Huang, Wenhao Computation and Language Artificial Intelligence Large language models (LLMs) often fail to learn effective long chain-of-thought (Long CoT) reasoning from human or non-Long-CoT LLMs imitation. To understand this, we propose that effective and learnable Long CoT trajectories feature stable molecular-like structures in unified view, which are formed by three interaction types: Deep-Reasoning (covalent-like), Self-Reflection (hydrogen-bond-like), and Self-Exploration (van der Waals-like). Analysis of distilled trajectories reveals these structures emerge from Long CoT fine-tuning, not keyword imitation. We introduce Effective Semantic Isomers and show that only bonds promoting fast entropy convergence support stable Long CoT learning, while structural competition impairs training. Drawing on these findings, we present Mole-Syn, a distribution-transfer-graph method that guides synthesis of effective Long CoT structures, boosting performance and RL stability across benchmarks. |
| title | The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.06002 |