rePIRL: Learn PRM with Inverse RL for LLM Reasoning

• URL: http://arxiv.org/abs/2602.07832v1
• Date: Sun, 08 Feb 2026 05:47:27 GMT
• Title: rePIRL: Learn PRM with Inverse RL for LLM Reasoning
• Authors: Xian Wu, Kaijie Zhu, Ying Zhang, Lun Wang, Wenbo Guo,
• Abstract summary: rePIRL is an inverse RL-inspired framework that learns effective PRMs with minimal assumptions about expert policies.<n>We show that our proposed learning framework can unify both online and offline PRM learning methods.<n>We also show the application of our trained PRM in test-time training, test-time scaling, and providing an early signal for training hard problems.
• Score: 20.51736503252891
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking. In LLM reasoning, existing works also explore various solutions for learning effective process reward models (PRM) with or without the help of an expert policy. However, existing methods either rely on strong assumptions about the expert policies (e.g., requiring their reward functions) or suffer intrinsic limitations (e.g., entropy collapse), resulting in weak PRMs or limited generalizability. In this paper, we introduce rePIRL, an inverse RL-inspired framework that learns effective PRMs with minimal assumptions about expert policies. Specifically, we design a dual learning process that updates the policy and the PRM interchangeably. Our learning algorithm has customized techniques to address the challenges of scaling traditional inverse RL to LLMs. We theoretically show that our proposed learning framework can unify both online and offline PRM learning methods, justifying that rePIRL can learn PRMs with minimal assumptions. Empirical evaluations on standardized math and coding reasoning datasets demonstrate the effectiveness of rePIRL over existing methods. We further show the application of our trained PRM in test-time training, test-time scaling, and providing an early signal for training hard problems. Finally, we validate our training recipe and key design choices via a detailed ablation study.

Related papers

• Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS [62.22644307952087]
  We introduce AIRL-S, the first natural unification of RL-based and search-based TTS.<n>We leverage adversarial inverse reinforcement learning (AIRL) combined with group relative policy optimization (GRPO) to learn a dense, dynamic PRM directly from correct reasoning traces.<n>Our results show that our unified approach improves performance by 9 % on average over the base model, matching GPT-4o.
  arXiv  Detail & Related papers  (2025-08-19T23:41:15Z)
• Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning [53.85659415230589]
  This paper systematically reviews widely adoptedReinforcement learning techniques.<n>We present clear guidelines for selecting RL techniques tailored to specific setups.<n>We also reveal that a minimalist combination of two techniques can unlock the learning capability of critic-free policies.
  arXiv  Detail & Related papers  (2025-08-11T17:39:45Z)
• 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)
• Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback [52.1410307583181]
  We useReinforcement Learning from Human Feedback to train language models (LMs) to follow complex human preferences.<n>As training progresses, the responses generated by the LM no longer resemble the responses seen by the reward model (RM)<n>We propose Off-Policy Corrected Reward Modeling to correct the RM using importance weighting, without requiring new labels or samples.
  arXiv  Detail & Related papers  (2025-07-21T11:19:04Z)
• Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning [49.21525229904197]
  We propose a novel data annotation method for PRMs specifically designed to score the long CoT reasoning process.<n>We introduce the concepts of Error Propagation and Error Cessation, enhancing PRMs' ability to identify both effective self-correction behaviors and reasoning based on erroneous steps.<n>Our PRM achieves superior performance across various metrics, including search guidance, BoN, and F1 scores.
  arXiv  Detail & Related papers  (2025-05-20T14:12:05Z)
• ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding [25.329712997545794]
  We propose Retrieval-Augmented Reasoning through Trustworthy Process Rewarding (ReARTeR)<n>ReARTeR enhances RAG systems' reasoning capabilities through post-training and test-time scaling.<n> Experimental results on multi-step reasoning benchmarks demonstrate significant improvements.
  arXiv  Detail & Related papers  (2025-01-14T05:56:26Z)
• Free Process Rewards without Process Labels [55.14044050782222]
  We show that an textitimplicit PRM can be obtained at no additional cost, by simply training an ORM on the cheaper response-level labels.<n>We show that our implicit PRM, when instantiated with the cross-entropy (CE) loss, is more data-efficient and can keep improving generation models even when trained with only one response per instruction.
  arXiv  Detail & Related papers  (2024-12-02T21:20:02Z)
• Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward Machine [2.087814874079289]
  We propose a knowledge-informed AutoPT framework called DRLRM-PT. We use reward machines (RMs) to encode domain knowledge as guidelines for training a PT policy. We show that RMs encoding more detailed domain knowledge demonstrated better PT performance compared to RMs with simpler knowledge.
  arXiv  Detail & Related papers  (2024-05-24T20:05:12Z)
• Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective [55.36819597141271]
  Inverse Reinforcement Learning (IRL) -- the problem of learning reward functions from demonstrations of an emphexpert policy -- plays a critical role in developing intelligent systems. This paper provides the first line of efficient IRL in vanilla offline and online settings using samples and runtime. As an application, we show that the learned rewards can emphtransfer to another target MDP with suitable guarantees.
  arXiv  Detail & Related papers  (2023-11-29T00:09:01Z)
• Jump-Start Reinforcement Learning [68.82380421479675]
  We present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-04-05T17:25:22Z)
• Self-Imitation Advantage Learning [43.8107780378031]
  Self-imitation learning is a Reinforcement Learning method that encourages actions whose returns were higher than expected. We propose a novel generalization of self-imitation learning for off-policy RL, based on a modification of the Bellman optimality operator.
  arXiv  Detail & Related papers  (2020-12-22T13:21:50Z)

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.