3 papers
cs.CL2026
Evidence-Calibrated Runtime Reconstruction for Agent Skills Across Heterogeneous Coding Agents
Xueping Gao
Agent Skills package reusable instructions and assets for tool-using language-model agents. Progressive loading creates failure boundaries poorly represented by session-, model-, o…
cs.CL2026
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
Xueping Gao, Jianwei Yang, Qiang Yang
Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee. We study the gap between finding a correct patch and retaining, ve…
cs.AI2026
CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits
Xue-Jian Gao, Deng Pan, Yueming Su +12
AI agents are now capable of writing, compiling, and iteratively optimizing low-level operator kernels on different hardware platforms. Existing benchmarks, however, focus almost e…