Yonggang Zhang
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
ML×2Software Eng.×1NLP×1
Frequent co-authors
Research Timeline
2026
Scaling Multi-Hop Training Data via Graph-Constrained Path Selection
The paper proposes a graph-constrained approach to scale multi-hop training data by decoupling path discovery from path verbalization, significantly expanding the usable corpus size for LLMs.
TTHE: Test-Time Harness Evolution
This paper introduces Test-Time Harness Evolution (TTHE), a method for optimizing LLM agent harnesses during evaluation using execution traces, without requiring gold labels or training.
Highlighted terms show continued research focus across papers
Papers
cs.SEcs.LGEmpiricalRecentJul 9, 2026
TTHE: Test-Time Harness Evolution
Jun Nie, Yonggang Zhang, Jun Song, Qianshu Cai +4 more
This paper introduces Test-Time Harness Evolution (TTHE), a method for optimizing LLM agent harnesses during evaluation using execution traces, without requiring gold labels or training.
View →
cs.CLcs.LGRecentMay 29, 2026