New Benchmark BTF-2: Evaluating Strategic Reasoning Capabilities of AI Forecasting Agents
A new arXiv paper introduces "Bench to the Future 2," a benchmark that systematically evaluates reasoning strategy diffe…
🏷️ Agent Evaluation
3 articles about 'Agent Evaluation'
BenchGuard: Using AI to Audit AI Benchmarks
A research team introduces the BenchGuard framework, the first to leverage frontier large language models to automatical…
GAIA-v2-LILT: A Multilingual AI Agent Benchmark That Goes Beyond Translation
Researchers introduce GAIA-v2-LILT, a refined pipeline combining functional alignment and cultural adaptation to address…
1