← Back to all news
arXiv Computer Vision

RECAP: Looking Once Is Not Enough for Vision-Language Reasoning

The paper introduces RECAP, a training method that enhances vision‑language models by incorporating temporally localized reactivation of image evidence—called visual revisit—into the reinforcement learning process. Visual revisit peaks are shown to predict correctness and causally improve performance; masking them hurts accuracy more than masking non‑peaks, while adding revisit peaks to failed reasoning partially restores correct answers. RECAP applies revisit‑conditioned advantage estimation, dynamic discounting, and gated value prediction to propagate final rewards through visually important reasoning steps, achieving significant gains on HallusionBench and other benchmarks without extra rewards or inference‑time changes.

Related stories

arXiv Computer Vision
Oct 16

Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs

The paper introduces Perception and Reasoning Attribution (PARA), a method that quantifies how much of a vision‑language model’s errors can be fixed by better perception versus stronger reasoning. PARA reveals that reinforcement learning (RL) benefits more from improving reasoning than perception, and motivates a new group‑relative attention distillation objective called GRAD. GRAD directly guides weaker rollouts toward the visual attention patterns of the best rollouts, consistently boosting performance across multiple model scales and benchmarks.

By Zeyuan Yang, Zhuohao Chen, Jiaben Chen, Yao Zhang, Maohao Shen, Chuang Gan
llmsreinforcement-learningefficiencymultimodalbenchmarks
More like this →
arXiv AI
Sep 28

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
llmsragreinforcement-learningefficiencymultimodalbenchmarks
More like this →
arXiv AI
Oct 9

VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning

VICO proposes a co‑evolutionary framework where a vision‑language model (actor) and an Environment‑as‑Rewriter (EnvRewriter) are trained together. The EnvRewriter edits visual structures—such as scene graphs, chart tables, or protected region masks—to generate new training samples whose difficulty is calibrated to the actor’s current performance via a pass‑rate reward. Across nine multimodal benchmarks, VICO‑8B outperforms its base model by up to +5.0 % on out‑of‑domain tasks and surpasses other co‑evolution baselines while requiring far fewer labeled samples.

By Meng Lu, Ligeng Zhu, Olivia Xiao, Yuchen Zhuang, Zihan Wang, Kuncheng Wu, Bangya Liu, Yu Wang, Charles Fleming, Wenqi Shi, Xuan Wang
llmsreinforcement-learningmultimodalbenchmarks
More like this →
arXiv Computer Vision
Aug 27

V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning

The paper introduces V‑Rubrics, a reinforcement‑learning framework that evaluates vision‑language model responses by breaking them into atomic propositions and scoring them on Visual Faithfulness, Reasoning Consistency, and Instruction Following. Using a fine‑tuned Qwen3‑VL‑8B‑Instruct model and a newly created 50K‑example V‑Rubrics dataset, the authors demonstrate that rubric‑based GRPO outperforms both a shared SFT baseline and an answer‑only GRPO, especially on knowledge‑oriented and visually grounded reasoning tasks.

By Shulin Tian, Minglun Li, Yuhao Dong, Hao Ding, Jiarui Yao, Haiwen Diao, Jingkang Yang, Hongyuan Zhu, Ziwei Liu
llmsreinforcement-learningfine-tuningmultimodalbenchmarks
More like this →