Abstract
Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal distinguishes overall response quality but leaves changes in visual-evidence use across generated tokens implicit. We introduce VAttnPO (Visual Attention-Guided Policy Optimization), which uses answer-conditioned visual attention to refine token-level credit while preserving the verifier-derived trajectory-mean advantage. A frozen old policy constructs a visual reference by teacher forcing the known correct answer and produces a visual distribution for each rollout token. VAttnPO measures their agreement in visual-attention space using Jensen--Shannon divergence, rather than reading guidance from teacher output-token distributions or introducing an attention-matching objective. Trajectory centering, relative-position weighting, and credit balancing turn this agreement into a zero-mean, position-aware correction to the GRPO sequence advantage. Token intervention, visual-index permutation, and trajectory analysis provide diagnostic evidence linking this signal to model behavior, visual correspondence, and generation position. On Qwen3-VL-8B-Instruct, VAttnPO raises six-task image AVE from 70.97 with GRPO to 73.50 and scores higher on every reported structured, video, and MME metric. Gains over GRPO also hold on Qwen2.5-VL-7B-Instruct and InternVL3-8B-Instruct.
Abstract (translated)
URL
https://arxiv.org/abs/2610.16735
