3 papers
cs.SE2026
CARET: Training-Free Test-Time Scaling for Repository-Level Code Completion
Jiajie Wang, Yutong Zhao, Kebin Peng +3
Retrieval-augmented generation (RAG) dominates repository-level code completion: it retrieves cross-file context (R), then decodes one greedy completion (G). Existing work mainly f…
cs.SE2026
Agent Skill Evolution: How Revisions Affect Coding Agents
Jiajie Wang, Yutong Zhao, Tianlin Li +4
Agent Skills, the SKILL.md files that tell an LLM coding agent how a project works, are revised like code, yet what a revision does to the agent is unknown. From 2,608 first/last r…
cs.SE2026
ExploreAI: Agentic Exploration Knowledge Bases for Reproducible Observable-Regression Testing of Black-Box VR and 3D Applications
Jiajie Wang, Kebin Peng, Wei Wang +3
Black-box VR and 3D applications are difficult to regression test because observable failures depend on where a tester moves, what objects are visible, and which views are captured…