ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward

• URL: http://arxiv.org/abs/2606.11209v1
• Date: Thu, 23 Apr 2026 21:25:47 GMT
• Title: ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward
• Abstract summary: Visual question answering increasingly requires multi-step reasoning.<n>Recent post-training with reinforcement learning can improve multimodal reasoning.<n>Most approaches rely on sparse outcome-only rewards.<n>We propose ProcessThinker, a practical post-training pipeline that provides step-level process rewards.
• Score: 27.341541512259216
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual question answering increasingly requires multi-step reasoning. Recent post-training with reinforcement learning under verifiable rewards (RLVR) and Group Relative Policy Optimization (GRPO) can improve multimodal reasoning, but most approaches rely on sparse outcome-only rewards. As a result, they struggle to tell whether an incorrect answer comes from a small mistake late in the reasoning or from an unhelpful trajectory from the start. A common solution is to train a process reward model (PRM) for step-level supervision, but this typically requires large-scale high-quality chain-of-thought annotations and additional training cost. We propose ProcessThinker, a practical post-training pipeline that provides step-level process rewards without training an explicit PRM. ProcessThinker first rewrites reasoning traces into a step-tagged format for cold-start supervised fine-tuning, then applies GRPO with a standard format reward and our rollout-based process reward. Concretely, for each intermediate step, we sample multiple continuations from that step and use the empirical success rate (final-answer verification) as the step reward. This gives dense credit assignment and encourages reasoning steps that more reliably support a correct conclusion, helping reduce inconsistent or self-contradictory progress across steps -- a key issue in logical reasoning. Across four challenging video benchmarks (Video-MMMU, MMVU, VideoMathQA, and LongVideoBench), ProcessThinker consistently improves over the baseline model Qwen3-VL-8B-Instruct

Related papers

• The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment [25.463488253598133]
  Process reward models (PRMs) enhance the reasoning capabilities of large language models (LLMs)<n>Outcome-supervised PRMs offer a scalable alternative by learning from final-answer correctness alone.<n>We propose Outcome-Supervised Process Reward Modeling via **L**earnable **C**redit **A**ssignment (**LCA**)
  arXiv  Detail & Related papers  (2026-06-26T05:38:08Z)
• Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization [74.91418266859297]
  Implicit process reward models (PRMs) provide fine-grained reward signals along the reasoning process.<n>PRMs suffer from a train-inference mismatch: training only constrains a sequence-level aggregate, whereas inference requires token-level scores to reflect local step quality.<n>We propose a novel Implicit Prefix-Value Reward Model (IPVRM), which directly learns a prefix-conditioned value function estimating the probability of eventual correctness.<n>We also propose Distribution-Level RL (DistRL), which computes TD advantages for both sampled tokens and high-probability candidate tokens.
  arXiv  Detail & Related papers  (2026-04-14T18:19:54Z)
• P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering [51.04492568024515]
  We introduce Probabilistic Process Supervision (P2S), a novel framework for fine-grained process rewards.<n>P2S provides fine-grained process rewards without requiring a separate reward model or human-annotated reasoning steps.
  arXiv  Detail & Related papers  (2026-01-28T14:35:20Z)
• Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models [33.398631680508814]
  We propose Answer-Consistent Reinforcement Learning that modifies the GRPO algorithm with an auxiliary consistency check.<n>We design a consistency-verification reward that grants a high reward only if both the original and the post-shuffle answers agree and are correct.<n>We evaluate ACRE on challenging Video Reasoning benchmarks and multimodal math reasoning benchmarks, achieving an average 2.2% and 1.5% improvement.
  arXiv  Detail & Related papers  (2025-10-11T08:32:52Z)
• Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards [40.905635870672945]
  Large language models for mathematical reasoning are typically trained with outcome-based rewards, which credit only the final answer.<n>In our experiments, we observe that this paradigm is highly susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability.<n>This is evidenced by a high incidence of false positives - solutions that reach the correct final answer through an unsound reasoning process.
  arXiv  Detail & Related papers  (2025-10-09T04:30:45Z)
• RRO: LLM Agent Optimization Through Rising Reward Trajectories [52.579992804584464]
  Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks.<n>In practice, agents sensitive to the outcome of certain key steps which makes them likely to fail the task.<n>We propose Reward Rising Optimization (RRO) to mitigate this issue.
  arXiv  Detail & Related papers  (2025-05-27T05:27:54Z)
• Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models [67.87579664988199]
  TON is a two-stage training strategy for vision-language models (VLMs)<n>It introduces a think-or-not format that serves as a cold start for selective reasoning.<n>TON can reduce the completion length by up to 90% compared to vanilla GRPO.
  arXiv  Detail & Related papers  (2025-05-22T16:13:29Z)
• R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization [86.32257216965229]
  We propose a new online reinforcement learning framework that enables MLLMs to self-improve reasoning ability via simple, effective and dense step-wise rewarding.<n>StepGRPO introduces two novel rule-based reasoning rewards: Step-wise Reasoning Accuracy Reward (StepRAR) and Step-wise Reasoning Validity Reward (StepRVR)<n>With the proposed StepGRPO, we introduce R1-VL, a series of MLLMs with outstanding capabilities in step-by-step reasoning.
  arXiv  Detail & Related papers  (2025-03-17T08:51:44Z)
• Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback [94.25162866972077]
  Step-KTO is a training framework that combines process-level and outcome-level binary feedback.<n>Our experiments show that Step-KTO significantly improves both final answer accuracy and the quality of intermediate reasoning steps.
  arXiv  Detail & Related papers  (2025-01-18T15:38:03Z)
• 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)

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.