2 papers
cs.SE2026
Better Specifications, Better Code: Fine-Tuning LLMs for Behavioral Contract Generation
Brhane Team, Tiantian Yang, Nikta Akbarpour +3
Large language models (LLMs) demonstrate strong code-generation capabilities but often struggle with functional correctness due to implicit or ambiguous behavioral requirements. We…
cs.CR2026
HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
Yajing Bai, Jinhao Duan, Jie Peng +4
Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions. Existing safety benchmar…