Author

Zhiheng Lyu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

Tencent WorkBuddy Bench is introduced, a multi-domain evaluation suite for coding agents, and its construction methodology, scoring protocol, and a cross-model leaderboard are documents, with a cross-model leaderboard across several model families.

Si-Qi Cai, Shao-Peng Chen, Xiang Fei et al. · arXiv.org · 4 citations

Jul 2026

Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance

This position paper argues that to claim a "long-horizon failure", benchmarks must compare actual full-task success against a baseline prediction built from short, individual stages, and calls the log-ratio between this prediction and actual success the horizon residual.

Chao Peng, Zhiheng Lyu, Peijie Dong et al. · arXiv.org · 0 citations