works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

cs.LG2026

Can Training Logs Make Model Comparisons More Precise?

Wei-Jung Huang

Comparing stochastically trained models requires estimating both a performance difference and its uncertainty from repeated runs. We study whether training logs from those same run…

cs.AI2026

ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision

Wei-Jung Huang, Bonan Shen

LLM-agent evaluations often produce task outcomes long before the full benchmark run is complete. A partial score is tempting to report, but it does not show whether the observed t…

cs.AI2026

How Many Tasks Are Enough for Agent Benchmark Decisions? A Replay Analysis of Public LLM Agent Benchmarks

Wei-Jung Huang

The paper investigates how many tasks are needed in public LLM agent benchmarks to reliably decide which agent performs better, by replaying task-level results from SWE-bench, AppW…

cs.AI2026

Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows

Wei-Jung Huang

Product data scientists often ask LLM-based agents to help with recurring execution tasks such as cleaning data, writing SQL, choosing statistical tests, and formatting results. Re…

cs.LG2026

AdaStop: Cost-Aware Early Stopping for DNN Test Selection

Bonan Shen, Wei-Jung Huang, Xin Liu +2

Existing methods for testing deep neural networks (DNNs) primarily prioritize test inputs likely to reveal model faults under a fixed labeling budget. In practice, choosing that bu…

cs.SE2026

LLM-Driven CI-CD Workflow Intelligence for Cyber Systems Engineering

Bonan Shen, Jiazhou Gao, Tao Ning +2

CI/CD workflows have become executable operational policy: they decide what gets built, tested, released, and deployed, and they mediate how maintainers interact with delivery infr…