Multimodal tool-using agents augment vision-language models with access to external information and capabilities, enabling them to solve knowledge-intensive and visually complex tasks that cannot be addressed using visual context alone. However, existing reinforcement learning pipelines largely train single-role agents...
Sheng-Qin Wang, Jie Jin, Xiao-Fan Li et al.· 0 citations
Agent systems deployed in dynamic environments continuously update their memories, skills, and runtime configurations, leading to evolving trajectories and challenges for persistent identity authentication. Existing text and agent watermarking methods struggle to achieve stable watermark embedding under dynamic environ...
Yu-Wei Zhong, Yu Cheng, Jiu-An Zhou et al.· 0 citations
SafeCoEvo is proposed, a test-time Harness-Guard co-evolution framework for LLM agent safety that enables the external safety system to continually adapt from accumulated runtime experience to achieve simultaneous gains in safety and task utility.
Yu Cheng, Yong-Kang Hu, Shuai Ma et al.· arXiv.org· 3 citations
This work proposes Tool-Grounded Multi-Agent Reasoning for Compositional Chemical Problem Solving (TMCS), a step-by-step multi-agent framework that formalizes chemical problem solving as an interpretable, tool-augmented workflow.
Sheng-Qin Wang, Jie Jin, Yu Cheng et al.· arXiv.org· 0 citations
The results suggest that the frontier of Physical AI depends not only on stronger action models, but also on executable harnesses that integrate perception, task understanding and reasoning, and action execution into a unified, verifiable, and feedback-driven system.