BenchGuard is the first LLM-based automated auditing framework for execution-based agent benchmarks, identifying 12 confirmed issues in ScienceAgentBench and matching 83.3% of expert findings on BIXBench at low cost.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
BenchGuard is the first LLM-based automated auditing framework for execution-based agent benchmarks, identifying 12 confirmed issues in ScienceAgentBench and matching 83.3% of expert findings on BIXBench at low cost.