paper-with-me

홈 › Papers

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs

2026-02-02 · Yanrui Du, Sendong Zhao, Yibo Gao, Danyang Zhao, Qika Lin, Ming Ma, Jiayun Li, Yi Jiang, Kai He, Qianyi Xu, Bing Qin, Mengling Feng arxiv

Large language models (LLMs) equipped with chain-of-thought (CoT) achieve strong performance and offer a window into LLM behavior. However, recent evidence suggests that improvements in CoT capabilities often come with redundant reasoning processes, motivating a key question: Can LLMs acquire a fast-thinking mode analogous to human System 1 reasoning? To explore this, our study presents a self-sampling framework based on activation steering for efficient CoT learning. Our method can induce style-aligned and variable-length reasoning traces from target LLMs themselves without any teacher guidance, thereby alleviating a central bottleneck of SFT-based methods-the scarcity of high-quality supervision data. Using filtered data by gold answers, we perform SFT for efficient CoT learning with (i) a human-like dual-cognitive system, and (ii) a progressive compression curriculum. Furthermore, we explore a self-evolution regime in which SFT is driven solely by prediction-consistent data of variable-length variants, eliminating the need for gold answers. Extensive experiments on math benchmarks, together with cross-domain generalization tests in medicine, show that our method yields stable improvements for both general and R1-style LLMs. Our data and model checkpoints can be found at https://github.com/DYR1/S3-CoT.

📄 PDF Abstract BibTeX arXiv:2602.01982

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Generalization

Similar Papers 제목 키워드 기반

SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression

2025-08-18 · Yuyang Xu, Yi Cheng, Haochao Ying, Zhuoyun Du 외 arxiv

Test-time scaling has proven effective in further enhancing the performance of pretrained Large Language Models (LLMs). However, mainstream post-training methods (i.e., reinforcement learning (RL) with chain-of-thought (…

Reinforcement Learning

Self-Consistency Improves Chain of Thought Reasoning in Language Models

2022-03-21 · Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le 외

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the …

ARCArithmetic ReasoningGSM8KLanguage Modelling+2

Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization

2026-04-08 · Yu Li, Sizhe Tang, Tian Lan arxiv

Reinforcement learning for Large Language Model agents is often hindered by sparse rewards in multi-step reasoning tasks. Existing approaches like Group Relative Policy Optimization treat sampled trajectories as independ…

Reinforcement Learning

DeepEdit: Knowledge Editing as Decoding with Constraints

2024-01-19 · Yiwei Wang, Muhao Chen, Nanyun Peng, Kai-Wei Chang

How to edit the knowledge in multi-step reasoning has become the major challenge in the knowledge editing (KE) of large language models (LLMs). The difficulty arises because the hallucinations of LLMs during multi-step r…

Informativenessknowledge editingMulti-hop Question AnsweringQuestion Answering

Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models

2023-02-01 · Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang 외

Large language models can perform various reasoning tasks by using chain-of-thought prompting, which guides them to find answers through step-by-step demonstrations. However, the quality of the prompts depends on the dem…