Showing 2026Show all
3 papers · 1 filter
cs.MA2026
VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience
Jianming Chen, Xuanbin Ye, Yawen Wang +3
Agents increasingly rely on reusable skills to encode task knowledge, tool-use procedures, and validation rules. Existing skill self-evolution methods primarily revise skills using…
cs.MA2026
OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
Jianming Chen, Yawen Wang, Junjie Wang +3
Tool-calling text-to-image (T2I) agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new…
cs.MA2026
Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents
Jianming Chen, Yawen Wang, Junjie Wang +4
Embodied agents in safety-critical applications such as Vision-Language Navigation (VLN) rely on multiple interdependent capabilities (e.g., perception, memory, planning, decision)…