Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning
We identify the Flow Moment, a reasoning pattern characterized by sustained, process-confirming verbalizations such as I'm doing, in contrast to the revision- and backtracking-oriented Aha Moment. We refer to their corresponding linguistic expressions as Flow Markers and Aha Markers, respectively. Based on this observation, we construct Flow-CoT by rewriting the discourse markers of original reasoning traces while preserving their underlying reasoning content, and use it as auxiliary supervision for on-policy self-distillation (OPSD). We further propose \textbf{Aha-Flow Distillation (AFD)}, a dual-mode extension of OPSD that pairs different forms of privileged information with correspondi...
| Authors | Xiaodong Wang, Peixi Peng |
|---|---|
| Primary category | cs.CL |
| Published | 7 September 2026 |
| Last updated at source | 7 September 2026 |
Connected in the knowledge graph
- Xiaodong/afd_mix_p100_verifiedDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.