2 papers
cs.CV2026
VAttnPO: Visual Attention-Guided Policy Optimization
Lihao Zheng, Zhenwei Shao, Zhou Yu +5
Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal distinguishes overall response qu…
cs.AI2026
MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
Jiawei Chen, Xintian Shen, Lihao Zheng +43
Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of auto…