Learning a Dense Reasoning Reward Model from Expert Demonstration via Inverse Reinforcement Learning

• URL: http://arxiv.org/abs/2510.01857v1
• Date: Thu, 02 Oct 2025 09:55:26 GMT
• Title: Learning a Dense Reasoning Reward Model from Expert Demonstration via Inverse Reinforcement Learning
• Authors: Claudio Fanconi, Nicolás Astorga, Mihaela van der Schaar,
• Abstract summary: We learn a dense, token-level reward model for process supervision directly from expert demonstrations.<n>The learned reasoning reward serves two complementary roles: (i) it provides step-level feedback to optimise a reasoning policy during training; and (ii) it functions at inference as a critic to rerank sampled traces under fixed compute budgets.
• Score: 50.20267980386502
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We reframe and operationalise adversarial inverse reinforcement learning (IRL) to large language model reasoning, learning a dense, token-level reward model for process supervision directly from expert demonstrations rather than imitating style via supervised fine-tuning. The learned reasoning reward serves two complementary roles: (i) it provides step-level feedback to optimise a reasoning policy during training; and (ii) it functions at inference as a critic to rerank sampled traces under fixed compute budgets. We demonstrate that our approach prioritises correctness over surface form, yielding scores that correlate with eventual answer validity and enabling interpretable localisation of errors within a trace. Empirically, on GSM8K with Llama3 and Qwen2.5 backbones, we demonstrate: (i) dense reasoning rewards can be used as a learning signal to elicit reasoning, and (ii) predictive performance is improved from reward-guided reranking (notably for Llama-based policies). By unifying training signals, inference-time selection, and token-level diagnostics into a single reasoning reward, this work suggests reusable process-level rewards with broad potential to enhance multi-step reasoning in language models.

Related papers

• Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation [46.38008143057758]
  Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable.<n>This work argues that reward modeling is not merely an implementation detail but a central architect of reasoning alignment.<n>Within this framework, we present a taxonomy of reward mechanisms, analyze reward hacking as a pervasive failure mode, and examine how reward signals unify challenges.
  arXiv  Detail & Related papers  (2026-02-10T00:45:24Z)
• Stabilizing Reinforcement Learning for Honesty Alignment in Language Models on Deductive Reasoning [27.42733470720954]
  We propose a reinforcement learning method that injects ground truth trajectories into rollouts, preventing early training collapse.<n>Our results demonstrate that this method stabilizes learning and significantly improves the overall reasoning performance.
  arXiv  Detail & Related papers  (2025-11-12T11:34:19Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards [48.55501117313608]
  We present chain of step reasoning for vision-language models, enabling assessing reasoning step quality accurately.<n>We present a simple, effective, and fully transparent framework, including the step-level reasoning data, process reward model (PRM), and reinforcement learning training.<n>We believe this paper serves as a baseline for vision-language models and offers insights into more complex multimodal reasoning.
  arXiv  Detail & Related papers  (2025-09-23T13:47:32Z)
• ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs [32.13266235550995]
  Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs)<n>Inspired by observations from human learning, we introduce a RL technique that integrates verifiable outcomes with the model's own confidence estimates.
  arXiv  Detail & Related papers  (2025-09-22T13:00:35Z)
• StepWiser: Stepwise Generative Judges for Wiser Reasoning [52.32416311990343]
  Process reward models address this by providing step-by-step feedback.<n>Inspired by recent advances, we reframe stepwise reward modeling from a classification task to a reasoning task itself.<n>We show it provides (i) better judgment accuracy on intermediate steps than existing methods; (ii) can be used to improve the policy model at training time; and (iii) improves inference-time search.
  arXiv  Detail & Related papers  (2025-08-26T17:45:05Z)
• Intra-Trajectory Consistency for Reward Modeling [67.84522106537274]
  We develop an intra-trajectory consistency regularization to enforce that adjacent processes with higher next-token generation probability maintain more consistent rewards.<n>We show that the reward model trained with the proposed regularization induces better DPO-aligned policies and achieves better best-of-N (BON) inference-time verification results.
  arXiv  Detail & Related papers  (2025-06-10T12:59:14Z)
• Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning [96.72185761508668]
  Planning at Test-time (IMPLANT) is a new meta-algorithm for imitation learning. We demonstrate that IMPLANT significantly outperforms benchmark imitation learning approaches on standard control environments.
  arXiv  Detail & Related papers  (2022-04-07T17:16:52Z)

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.