MMODELYST
Papers/Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning
PAP

Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning

Jun 8, 2026

arXiv
Abstract

Visual reasoning requires integrating evidence distributed across regions, attributes, and relations, making single-chain reasoning prone to early perceptual commitment and hallucination. We propose Visual Para-Thinker++, a single-policy multi-agent framework in which one shared MLLM policy is instantiated as role-conditioned Main, Worker, and Summary Agents. The Main Agent decomposes the task with fixed allocation patterns; Worker Agents reason in parallel under context isolation; and the Summary Agent reconciles full Worker reasoning traces rather than majority-voting on final labels. The shared policy is trained by Multi-Agent Capability Injection and Role-Decoupled Multi-Agent Optimization, which assign role-specific rewards and advantages to corresponding token segments to reduce gradient conflict among collaborative roles. A native inference engine enables efficient multi-agent rollout through shared visual prefix and KV cache reuse. Across V*, CountBench, the RefCOCO family, and HallusionBench, Visual Para-Thinker++ consistently outperforms single-trajectory and inference-time parallel baselines, with especially strong gains on hallucination-sensitive visual reasoning.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Haoran Xu, Hongyu Wang, Yifei Gao, Jiaze Li, Zizhao Tong, Xiaofeng Zhang, Xiaosong Yuan
Your notes (browser-local)
saved
Cross-links
No linked entities.
arXiv:2606.09290