Filtered to agent-based systems · clear filter
This paper introduces FrontierChallenge, a benchmark to evaluate the completion of end-to-end scientific workflows, and investigates the performance of various models in completing these workflows. Practitioners might care about this research to improve the accuracy of scientific workflow completion evaluations.
This paper introduces Mechanist, a system that uses AI to discover the underlying mechanisms of intelligence, allowing for better understanding and control of AI models. Practitioners might care because Mechanist can identify safety risks and improve model performance.
This paper develops a system to automatically optimize the design of harnesses for LLM agents, which can improve their reliability on long-horizon tasks. Practitioners might care about this because it could lead to more robust and performant agent systems.