2 papers
cs.SE2026
DepthBenchCAD: When Does Deeper Auditing Yield More Reliable Conclusions?
Hongye Yang, Zhihao Xie, Shengjun Xiong +1
Generative CAD models are expected to remain behaviorally correct after parameter edits, so increasing the number of edit checks is often treated as a direct route to more reliable…
cs.AI2026
PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation
Hongye Yang, Zhihao Xie, Shengjun Xiong
Long-horizon tool agents often make useful progress without reaching terminal success, motivating partial-credit evaluation. Yet evaluators may reward milestones that were temporar…