AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

POLIA: Policy Optimization with Visual-Object-Level Intrinsic Advantage for Multimodal Reasoning

Yiran Zeng, Da Chen, Hangyu Mao, Yuanxing Zhang, Pengfei Wan, Mengchen Zhao

ICML 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Reinforcement learning for visual reasoning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes POLIA, a group-based RL method that adds visual-object-level intrinsic advantages to address reasoning hallucination in multimodal LLM reasoning.

Problem

Group-based RL methods for LLM text reasoning lack sufficient modeling of multimodal information, causing significant reasoning hallucination in multimodal reasoning.

Approach

Introduces two advantage computation stages over candidate responses that assign intrinsic advantages at the visual-object level, so that policy updates reward grounding in visual objects rather than only final answer correctness.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add visual-object-level intrinsic advantage to GRPO (POLIA vs GRPO, 7B)Qwen2.5-VL-7B · VSRACC (%): +22.3%Improved
add visual-object-level intrinsic advantage to GRPO (7B)Qwen2.5-VL-7B · TallyQAACC (%): +8.7%Improved
add visual-object-level intrinsic advantage to GRPO (7B)Qwen2.5-VL-7B · GQAACC (%): +11.3%Improved
add visual-object-level intrinsic advantage to GRPO (7B)Qwen2.5-VL-7B · MathVistaACC (%): +9.3%Improved
add intrinsic advantage to RL baselines (3B)Qwen2.5-VL-3B · VSRACC (%): +18.4%Improved
add intrinsic advantage to RL baselines (3B)Qwen2.5-VL-3B · TallyQAACC (%): +7.2%Improved
add answer-level extrinsic advantage (ablation)POLIA · VSR and TallyQA trainingnormalized training rewardImproved
add object-level intrinsic advantage (ablation)POLIA · VSR and TallyQA trainingnormalized training rewardImproved
add intrinsic advantage to reduce visual object group count (ablation)POLIA · TallyQA (N=8)number of visual object groups: increases by 50%Improved
increase generation size from 8 to 16 or 24 (ablation)POLIA · TallyQAACCImproved
increase generation size from 16 to 24 (ablation)POLIA · TallyQAACCNo clear effect
add intrinsic advantage computation overheadPOLIA-3B · per-iteration training timeseconds: 0.002 sNo clear effect

Experimental setup

Builds on: GRPO

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy