3 papers
cs.SE2026
VITAL-RAG: Invariance Race for Context Allocation in Coding Agents
Zijian Lu, Yonghua Lu, Mingcai Chen +4
Coding agents often retrieve code from an entire repository, but only limited evidence can fit into the final model input. Conventional retrieval-augmented generation (RAG) for cod…
cs.CV2026
Prior Directions: Why GUI Grounding Gets Locked in the Past
Weile Gong, Zijian Lu, Mingcai Chen +3
Vision-language models often use descriptions of earlier visual states to make decisions about the current scene. When the scene changes, stale language can redirect an otherwise c…
cs.SE2026
ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
Zijian Lu, Yiping Zuo, Yupeng Nie +4
Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottleneck is not only skill generation quali…