activity
20242026
most citedEvaluating Large Language Models in Scientific Discovery

3 citations · 3 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks

Xinming Tu, Tianze Wang, Yingzhou +4

As benchmarks grow in complexity, many apparent agent failures are not failures of the agent at all - they are failures of the benchmark itself: broken specifications, implicit ass…