Off-Policy Value-Based Reinforcement Learning for Large Language Models

• URL: http://arxiv.org/abs/2603.23355v1
• Date: Tue, 24 Mar 2026 15:55:02 GMT
• Title: Off-Policy Value-Based Reinforcement Learning for Large Language Models
• Abstract summary: ReVal is a Bellman-update-based method that combines stepwise signals capturing internal consistency with trajectory-level signals derived from outcome verification.<n>On DeepSeek-R1-Distill-1.5B, ReVal improves training efficiency and achieves improvement of 2.7% in AIME24 and 4.5% in out-of-domain benchmark GPQA over GRPO.
• Score: 25.962820072445222
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Improving data utilization efficiency is critical for scaling reinforcement learning (RL) for long-horizon tasks where generating trajectories is expensive. However, the dominant RL methods for LLMs are largely on-policy: they update each batch of data only once, discard it, and then collect fresh samples, resulting in poor sample efficiency. In this work, we explore an alternative value-based RL framework for LLMs that naturally enables off-policy learning. We propose ReVal, a Bellman-update-based method that combines stepwise signals capturing internal consistency with trajectory-level signals derived from outcome verification. ReVal naturally supports replay-buffer-based training, allowing efficient reuse of past trajectories. Experiments on standard mathematical reasoning benchmarks show that ReVal not only converges faster but also outperforms GRPO in final performance. On DeepSeek-R1-Distill-1.5B, ReVal improves training efficiency and achieves improvement of 2.7% in AIME24 and 4.5% in out-of-domain benchmark GPQA over GRPO. These results suggest that value-based RL is a practical alternative to policy-based methods for LLM training.

Related papers

• REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge [83.2858110368572]
  We propose textbfREAL (underlineREgression-underlineAware Reinforcement underlineLThought), a principled RL framework designed to optimize regression rewards.<n>We show that REAL consistently outperforms both regression-aware SFT baselines and standard RL methods.
  arXiv  Detail & Related papers  (2026-03-17T21:19:08Z)
• Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates [53.3717573880076]
  We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates.<n>JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly.<n>Experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods.
  arXiv  Detail & Related papers  (2026-01-26T14:16:51Z)
• DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning [37.20873499361773]
  We propose a unified framework for training masked diffusion large language models (dLLMs) to reason better (furious)<n>We first unify the existing baseline approach by proposing to train surrogate policies via off-policy RL, whose likelihood is much more tractable as an approximation to the true dLLM policy.<n>We also propose a new direction of joint training efficient samplers/controllers of dLLMs policy. Via RL, we incentivize dLLMs' natural multi-token prediction capabilities by letting the model learn to adaptively allocate an inference threshold for each prompt.
  arXiv  Detail & Related papers  (2025-10-02T16:57:24Z)
• Reinforcement Learning on Pre-Training Data [55.570379963147424]
  We introduce Reinforcement Learning on Pre-Training data (R), a new training-time scaling paradigm for optimizing large language models (LLMs)<n>R enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL)<n>Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of R.
  arXiv  Detail & Related papers  (2025-09-23T17:10:40Z)
• Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control [50.316067647636196]
  This paper introduces Succeed or Learn Slowly (SoLS), a novel off-policyReinforcement learning algorithm evaluated on mobile app control tasks.<n>SoLS improves sample efficiency when fine-tuning foundation models for user interface navigation via a modified off-policy actor-critic approach.<n>We augment SoLS with Successful Transition Replay (STR), which prioritises learning from successful interactions.
  arXiv  Detail & Related papers  (2025-09-01T18:55:27Z)
• Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers [57.95157497749428]
  We propose RL$V$ that augments any value-free'' RL method by jointly training the LLM as both a reasoner and a generative verifier.<n> RL$V$ boosts MATH accuracy by over 20% with parallel sampling and enables $8-32times$ efficient test-time compute scaling.
  arXiv  Detail & Related papers  (2025-05-07T22:41:26Z)
• 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)

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.