View PDF HTML (experimental)

Abstract: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.
Comments: Preprint
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2601.06002 [cs.CL]
  (or arXiv:2601.06002v2 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2601.06002

arXiv-issued DOI via DataCite

Submission history

From: Qiguang Chen [view email]
[v1] Fri, 9 Jan 2026 18:39:01 UTC (8,412 KB)
[v2] Tue, 13 Jan 2026 18:21:01 UTC (8,412 KB)