activity
20242026
collaborators

20 papers

cs.AI2026

MemoHarness: Agent Harnesses That Learn from Experience

Yue Huang, Wenjie Wang, Han Bao +7

MemoHarness is a framework that automatically adapts the control layer (harness) of large language model agents by learning from past executions, using a dual‑layer experience bank…

cs.SE2026

Fail-Aware and Explainable Test Oracle Prediction

Yue Zhao, Binish Tanveer, Jelena Zdravkovic

The paper introduces FOCAL, a code‑language‑model based system that predicts whether a test prefix will pass or fail and provides statement‑level explanations, improving fault dete…

cs.AI2026

SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents

Tianming Sha, Yue Zhao, Lichao Sun +1

Autonomous AI agents can execute complex tasks with limited human review, yet they often lack the grounded operational knowledge to make their outputs not just executable but corre…

cs.CL2026

SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution

Aojie Yuan, Yi Nian, Haiyue Zhang +2

Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary label…

cs.AI2026

Agent Safety Is Action Alignment

Shawn Li, Yue Zhao

Large language models increasingly act as agents: they call tools, move money, delete records, and send messages on a user's behalf. To keep them safe, practitioners imported the c…

cs.LG2026

GRADE: Graph Representation of LLM Agent Dependency and Execution

Yue Zhao

Can one graph represent every kind of LLM agent's run? A trace records what each step did, never what it relied on, the state it read, and the results it reused. GRADE recovers tha…