Provides an academic benchmark for rigorously evaluating AI agent capabilities in real scientific research workflows.
Stanford researchers released Terminal-Bench-Science 0.1, a with 70 expert-curated scientific workflows where Claude Opus achieved only a 30% resolution rate.
Toby Ord explores the mathematical dynamics of intelligence explosions where AI assists AI R&D, showing singular growth is harder than economic models suggest.
Presents Persona-Execution Separation, an architecture pattern for enterprise LLM agents that keeps execution auditable while allowing persona instructions to evolve freely.
Researchers propose measuring 'monitorability disposition' in large reasoning models to proactively understand model behavior rather than reactively filtering outputs.
GPT-5.6 can design near-optimal algorithms for operations research problems like inventory control and queueing networks, matching or beating specialized methods with minimal human input.
Researchers propose TTPO, a novel test-time policy optimization method that enhances large language models' mathematical reasoning without ground-truth labels.
