An agent can complete a task while exhibiting undesirable behavior during execution. Developers need tests for the specific behaviors encountered in deployment, beyond fixed benchmark suites. We present TraceDance, an agent system that constructs targeted benchmarks from deployment traces for user-specified undesirable...
De-Hai Min, Dao-An Zhang, Yiming Zeng et al.· 0 citations
TSRouter, a graph-based dynamic routing framework that demonstrates robust zero-shot plug-and-play generalization to unseen models and novel tasks and preserves high performance while reducing computational overhead through cost-aware optimization.
Fangxu Yu, Tao Feng, De-Hai Min et al.· arXiv.org· 3 citations
EpiQAL provides fine-grained diagnostic signals for evidence-grounding, inferential reasoning, and conclusion reconstruction for epidemiological question answering over research literature, comprising three subsets built from open-access articles across diverse diseases.
Mingyang Wei, De-Hai Min, Zewen Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.