arXiv AI June 30, 2026 By Chao Wang, Hongtao Tian, Tao Yang, Yunsheng Shi, Ting Yao, Wenbo Ding

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners

arXiv:2606. 29296v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is a default recipe for process-supervised reinforcement learning of LLM reasoners, and dense process supervision -- via learned process reward models (PRMs) or on-policy-distillation KL signals -- is a common way to densify its otherwise weak outcome reward.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 27

Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning

arXiv:2507. 01551v3 Announce Type: replace Abstract: Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs).

By Wu Fei, Shuxian Liang, Yibo Yang, Yang Lin, Jing Tang, Lei Chen, Xiansheng Hua, Hao Kong

llms reinforcement-learning

arXiv Machine Learning

Jul 7

Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models

arXiv:2607. 02869v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving mathematical reasoning in language models.

By Anagha Radhakrishna Palandye, Rebecca Glick, Osheen Kaul

llms reinforcement-learning fine-tuning

arXiv AI

6d ago

Stepwise Intrinsic Rewards for Reasoning in Large Language Models

The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.

By Xiangwei Wang, Wei Wang, Ken Chen, Nanduni Nimalsiri, Sachith Seneviratne, Saman Halgamuge

llms rag reinforcement-learning efficiency multimodal benchmarks

arXiv AI

Jun 11

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

arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.

By Jingpei Wu, Xiao Han, Weixiang Shen, Boer Zhang, Zifeng Ding, Volker Tresp

llms nlp reinforcement-learning fine-tuning multimodal benchmarks

arXiv Computation and Language

Sep 7

ConsensusBench: Benchmark of Consensus Nodes for LLM Reasoning via Outcome Reward Densifying

ConsensusBench is a new dataset that supplies rule‑based process‑level signals for large language model reasoning. It identifies key intermediate conclusions—called Consensus Nodes—by filtering correct trajectories and clustering semantically equivalent statements. By incorporating a process reward derived from these nodes into GRPO‑style reinforcement learning, the authors create ConsensusPR, which reduces reward sparsity and improves performance on benchmarks such as AIME, GSM8K, and MATH‑500.

By Shi-Qi Yan, Chao-Hong Tan, Qian Chen, Wen Wang, Xiangang Li, Zhen-Hua Ling

llms reinforcement-learning efficiency benchmarks

arXiv Computer Vision

Aug 28

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

The paper introduces Echo-GRPO, a method that rewrites privileged reasoning traces into a model’s own idiolect to align off‑policy supervision with the student policy’s vocabulary. By preserving semantics through Dual‑Reference Decoding, Echo‑GRPO mitigates gradient clipping on critical reasoning tokens and improves reasoning distillation. The approach is instantiated as VideoEcho‑R1 for video reasoning, yielding consistent gains across multiple multimodal LLM backbones and benchmarks, and it can be applied as a plug‑in to both RL and supervised fine‑tuning frameworks.

By Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, Hyunwoo J. Kim

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks