3 papers
cs.AI2026
Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks
Zichuan Fu, Junjia Qi, Xian Wu +4
Agentic workflows organize complex tasks into reusable procedures. However, invoking an LLM at every step incurs repeated inference costs and delays. We propose a framework for sel…
cs.CV2026
GUI-Lens: Enabling Precise GUI Grounding for Off-the-Shelf VLMs via Coarse-to-Fine Cropping
Zichuan Fu, Shirong Wang, Wenlin Zhang +10
GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resolution, densely populated inter…
cs.AI2026
LLM-as-Code: Agentic Programming for Agent Harness
Junjia Qi, Zichuan Fu, Jingtong Gao +4
Every major LLM agent framework gives the LLM the role of orchestrator; the model decides what to do next, when to call tools, and when to stop. We argue that token explosion, cont…