ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding

• URL: http://arxiv.org/abs/2508.19576v2
• Date: Mon, 08 Sep 2025 13:12:19 GMT
• Title: ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding
• Authors: Sining Zhoubian, Dan Zhang, Jie Tang,
• Abstract summary: This paper introduces ReST-RL, a unified LLM RL paradigm.<n>It combines an improved GRPO algorithm with a meticulously designed test time decoding method assisted by a value model (VM)<n>We conduct extensive experiments on coding problems to verify the validity of the proposed RL paradigm.
• Score: 15.051729280454454
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method GRPO faces failure due to insignificant reward variance, while verification methods based on process reward models (PRMs) suffer from difficulties with training data acquisition and verification effectiveness. To tackle these problems, this paper introduces ReST-RL, a unified LLM RL paradigm that significantly improves LLM's code reasoning ability by combining an improved GRPO algorithm with a meticulously designed test time decoding method assisted by a value model (VM). As the first stage of policy reinforcement, ReST-GRPO adopts an optimized ReST algorithm to filter and assemble high-value training data, increasing the reward variance of GRPO sampling, thus improving the effectiveness and efficiency of training. After the basic reasoning ability of LLM policy has been improved, we further propose a test time decoding optimization method called VM-MCTS. Through Monte-Carlo Tree Search (MCTS), we collect accurate value targets with no annotation required, on which VM training is based. When decoding, the VM is deployed by an adapted MCTS algorithm to provide precise process signals as well as verification scores, assisting the LLM policy to achieve high reasoning accuracy. We conduct extensive experiments on coding problems to verify the validity of the proposed RL paradigm. Upon comparison, our approach significantly outperforms other reinforcement training baselines (e.g., naive GRPO and ReST-DPO), as well as decoding and verification baselines (e.g., PRM-BoN and ORM-MCTS) on well-known coding benchmarks of various levels (e.g., APPS, BigCodeBench, and HumanEval), indicating its power to strengthen the reasoning ability of LLM policies. Codes for our project can be found at https://github.com/THUDM/ReST-RL.

Related papers

• Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner [31.033131727230277]
  Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL)<n>We propose a novel intrinsic signal-driven generative process evaluation mechanism operating at the thought level to address major bottlenecks in RL-based training.<n>Experiments on 1.5B and 7B parameter LRMs demonstrate that our method achieves higher problem-solving accuracy with significantly fewer training samples than outcome-only reward baselines.
  arXiv  Detail & Related papers  (2025-07-31T07:54:58Z)
• 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)
• Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization [22.67700436936984]
  We introduce Direct Advantage Policy Optimization (DAPO), a novel step-level offline reinforcement learning algorithm.<n>DAPO employs a critic function to predict the reasoning accuracy at each step, thereby generating dense signals to refine the generation strategy.<n>Our results show that DAPO can effectively enhance the mathematical and code capabilities on both SFT models and RL models, demonstrating the effectiveness of DAPO.
  arXiv  Detail & Related papers  (2024-12-24T08:39:35Z)
• Process Supervision-Guided Policy Optimization for Code Generation [15.943210767010045]
  Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation.<n>We propose a Process Reward Model (PRM) that delivers dense, line-level feedback on code correctness during generation, mimicking human code refinement.
  arXiv  Detail & Related papers  (2024-10-23T07:22:33Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Let's reward step by step: Step-Level reward model as the Navigators for Reasoning [64.27898739929734]
  Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase. We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs. To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
  arXiv  Detail & Related papers  (2023-10-16T05:21:50Z)
• Reinforced Self-Training (ReST) for Language Modeling [56.75447441157628]
  Reinforcement learning from human feedback (RLHF) can improve the quality of large language model's (LLM) outputs by aligning them with human preferences. We propose a simple algorithm for aligning LLMs with human preferences inspired by growing batch reinforcement learning (RL), which we call Reinforced Self-Training (ReST) Our results show that ReST can substantially improve translation quality, as measured by automated metrics and human evaluation on machine translation benchmarks in a compute and sample-efficient manner.
  arXiv  Detail & Related papers  (2023-08-17T14:12:48Z)

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.