ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
The paper introduces ThoughtFold, a framework designed to improve the efficiency of Large Reasoning Models (LRMs) by addressing redundant explorations in long reasoning chains. By employing introspective preference learning, ThoughtFold penalizes unnecessary steps and encourages more concise reasoning paths. Experimental results indicate that this approach significantly reduces token usage while maintaining high accuracy.
- ▪ThoughtFold aims to mitigate redundant explorations in long reasoning chains of LRMs.
- ▪The framework utilizes fine-grained preference learning to optimize reasoning efficiency.
- ▪Experiments show a 56% reduction in token usage for DeepSeek-R1-Distill-Qwen-7B while preserving state-of-the-art accuracy.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2606.03503 |
| Publication time | Wed, 03 Jun 2026 00:00:00 -0400 |
| Retrieval time | 2026-06-03T04:11:55.408Z |
| Last seen | 2026-06-03T04:11:55.408Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 7MHshHVtxNyT |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2606.03503 (cs) [Submitted on 2 Jun 2026] Title:ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning Authors:Ziyan Liu, Xueda Shen, Yuzhe Gu, Songyang Gao, Kuikun Liu, Guangran Cheng, Chengqi Lyu, Dahua Lin, Wenwei Zhang, Kai Chen View a PDF of the paper titled ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning, by Ziyan Liu and 9 other authors View PDF Abstract:Large Reasoning Models (LRMs) have achieved remarkable progress thanks to Reinforcement Learning with Verifiable Rewards (RLVR) on Chain-of-Thoughts (CoTs).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
