SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

• URL: http://arxiv.org/abs/2506.19767v1
• Date: Tue, 24 Jun 2025 16:31:37 GMT
• Title: SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
• Authors: Yuqian Fu, Tinghong Chen, Jiajun Chai, Xihuai Wang, Songjun Tu, Guojun Yin, Wei Lin, Qichao Zhang, Yuanheng Zhu, Dongbin Zhao,
• Abstract summary: Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge.<n>We propose Supervised Reinforcement Fine-Tuning (SRFT), a single-stage method that unifies both fine-tuning paradigms through entropy-aware weighting mechanisms.<n>Extensive experiments show that SRFT achieves 59.1% average accuracy, outperforming zero-RL methods by 9.0% on five mathematical reasoning benchmarks and 10.9% on three out-of-distribution benchmarks.
• Score: 20.442971494407896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge. Through comprehensive analysis of token distributions, learning dynamics, and integration mechanisms from entropy-based perspectives, we reveal key differences between these paradigms: SFT induces coarse-grained global changes to LLM policy distributions, while RL performs fine-grained selective optimizations, with entropy serving as a critical indicator of training effectiveness. Building on these observations, we propose Supervised Reinforcement Fine-Tuning (SRFT), a single-stage method that unifies both fine-tuning paradigms through entropy-aware weighting mechanisms. Our approach simultaneously applies SFT and RL to directly optimize the LLM using demonstrations and self-exploration rollouts rather than through two-stage sequential methods. Extensive experiments show that SRFT achieves 59.1% average accuracy, outperforming zero-RL methods by 9.0% on five mathematical reasoning benchmarks and 10.9% on three out-of-distribution benchmarks.

Related papers

• RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization [86.30192066451256]
  We propose RL-PLUS, a novel hybrid-policy optimization approach for Large Language Models (LLMs)<n> RL-PLUS synergizes internal exploitation with external data to achieve stronger reasoning capabilities and surpass the boundaries of base models.<n>We provide both theoretical analysis and extensive experiments to demonstrate the superiority and generalizability of our approach.
  arXiv  Detail & Related papers  (2025-07-31T23:55:29Z)
• Revisiting LLM Reasoning via Information Bottleneck [57.519119962528166]
  Large language models (LLMs) have recently demonstrated remarkable progress in reasoning capabilities through reinforcement learning with verifiable rewards (RLVR)<n>We present a theoretical characterization of LLM reasoning grounded in information bottleneck (IB) principle.<n>We propose IB-aware reasoning optimization (IBRO), a framework that encourages reasoning trajectories to be both informative about the final correct answer and generalizable.
  arXiv  Detail & Related papers  (2025-07-24T13:14:25Z)
• Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling [35.64557242726578]
  Prefix-RFT is a hybrid approach that synergizes learning from both demonstration and exploration.<n>It not only surpasses the performance of standalone SFT and RFT but also outperforms parallel mixed-policy RFT methods.
  arXiv  Detail & Related papers  (2025-07-02T13:04:09Z)
• Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs [51.21041884010009]
  Ring-lite is a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL)<n>Our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-06-17T17:12:34Z)
• Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections [65.36449542323277]
  We present a unified theoretical framework bridgingSupervised Fine-Tuning (SFT) and preference learning in Large Language Model (LLM) post-training.<n>We propose a simple yet effective learning rate reduction approach that yields significant performance improvements.
  arXiv  Detail & Related papers  (2025-06-15T05:42:29Z)
• DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management [18.953750405635393]
  Decoupled Group Reward Optimization (DGRO) is a general RL algorithm for Large Language Models (LLMs) reasoning.<n>We show that DGRO achieves state-of-the-art performance on the Logic dataset with an average accuracy of 96.9%, and demonstrates strong generalization across mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-05-19T10:44:49Z)
• SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM [18.275547804539016]
  Two-Staged history-Resampling Policy optimization surpasses the performance of DeepSeek-R1-Zero-32B on the AIME24 and LiveCodeBench benchmarks.<n>We introduce two key methodological innovations: (1) a two-stage cross-domain training paradigm designed to balance the development of mathematical reasoning and coding proficiency, and (2) History Resampling (HR), a technique to address ineffective samples.
  arXiv  Detail & Related papers  (2025-04-19T13:06:03Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling [52.34735382627312]
  Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks.<n>Existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling.<n>We present T1 to scale reinforcement learning by encouraging exploration and understand inference scaling.
  arXiv  Detail & Related papers  (2025-01-20T18:33:33Z)
• Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging [11.223074654129915]
  Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. We propose to mitigate this imbalance by merging SFT models fine-tuned with different data orders.
  arXiv  Detail & Related papers  (2024-10-01T08:44:31Z)
• Latent Variable Representation for Reinforcement Learning [131.03944557979725]
  It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
  arXiv  Detail & Related papers  (2022-12-17T00:26:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.