12 papers
Agentic Auto-Research is Fuzz Testing
Yifeng He, Jicheng Wang, Yinzhe Zhao +2
Autonomous research agents can generate experiments faster than researchers can validate them. Researchers have responded by scaling the proposer and ranking more samples with a le…
LLM-Based Invariant Testing for Software Functional Bugs
Ruogu Yang, Yifeng He, Yundi Xu +2
Manually writing unit tests to uncover functional bugs in software libraries is not only time-consuming but also requires a deep understanding of the intended semantics of the APIs…
Is Progressive Disclosure All You Need for Long-Context Agents?
Yifeng He, Yinzhe Zhao, Jicheng Wang +1
Long-document question answering usually forces a choice between loading the whole document into the context window and bolting on a separate retriever. Agentic AI suggests a broad…
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Xiangyi Li, Yimin Liu, Wenbo Chen +75
Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to m…
Code Generation by Differential Test Time Scaling
Yifeng He, Ethan Wang, Jicheng Wang +2
Test-time scaling has emerged as a promising approach for improving code generation by exploring large solution spaces at inference time. However, existing methods often rely on pu…
ContractBench: Can LLM Agents Preserve Observation Contracts?
Jicheng Wang, Yifeng He, Zili Wang +3
Tool-augmented LLM agents call APIs whose intermediate outputs, such as presigned URLs, session tokens, and OAuth state parameters, are observation contracts: artifacts whose later…