6 citations · 12 across the 7 of their papers we have counts for
3 papers · 1 filter
The Limits of Inference Scaling Through Resampling
Benedikt Stroebl, Sayash Kapoor, Arvind Narayanan
Recent research has generated hope that inference scaling, such as resampling solutions until they pass verifiers like unit tests, could allow weaker models to match stronger ones.…
CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
Zachary S. Siegel, Sayash Kapoor, Nitya Nadgir +2
AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the development of useful agents, we need benchmark…
AI Agents That Matter
Sayash Kapoor, Benedikt Stroebl, Zachary S. Siegel +2
AI agents are an exciting new research direction, and agent development is driven by benchmarks. Our analysis of current agent benchmarks and evaluation practices reveals several s…