SOURCE-LINKED INTELLIGENCE

Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Reinforcement learning with verifiable rewards (RLVR) has significantly improved the reasoning capabilities of large vision-language models (LVLMs). However, standard on-policy RLVR algorithms face a critical optimization bottleneck in preserving and reinforcing visually grounded reasoning behaviors: valuable visually-grounded reasoning trajectories are discarded after a single update, while uniform token advantage allocation prevents the model from reinforcing critical perception or reasoning steps. To bridge this gap, we propose PIVOT, a dual-level learning framework that anchors policy opti

Read original source ↗ Open in workspace

recordType

paper

region

Global