arXiv:2602. 07267v2 Announce Type: replace Abstract: Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty.
arXiv:2608. 05797v1 Announce Type: new Abstract: Task difficulty dictates an agent's likelihood of success, and estimating it without rollouts means forecasting this directly from a task description before executing costly simulations in stateful environments.
Task difficulty dictates an agent's likelihood of success, and estimating it without rollouts means forecasting this directly from a task description before executing costly simulations in stateful environments. Reliable estimates would therefore allow environment designers to calibrate evaluation benchmarks and construct progressive training curricula.
arXiv:2503. 14499v4 Announce Type: replace Abstract: Despite rapid progress on AI benchmarks, the real-world meaning of benchmark performance remains unclear.
arXiv:2502. 20502v2 Announce Type: replace Abstract: Recent advances in Artificial Intelligence (AI) have yielded powerful computational models that, by learning from vast amounts of human-generated data, are increasingly posited as approximate models of human cognition.
arXiv:2602. 12147v4 Announce Type: replace Abstract: Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.
arXiv:2604. 00594v2 Announce Type: replace Abstract: As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, understanding which tasks will challenge agents and why becomes increasingly difficult.
arXiv:2606. 07157v1 Announce Type: new Abstract: Many efforts to ensure frontier AI models are safe rely on monitoring their chain-of-thought (CoT) reasoning.
arXiv:2607. 16239v1 Announce Type: new Abstract: AI judges offer a scalable, low-cost alternative to human evaluation, but their outputs can be biased relative to human preferences and highly item-dependent, varying across judges, tasks, and domains.
arXiv:2606. 26429v1 Announce Type: new Abstract: Current LLM evaluation relies on two complementary but often disconnected signals: static benchmarks with objective correctness labels and arena-style preference data that better reflect open-ended user interactions.
arXiv:2607. 15190v1 Announce Type: new Abstract: AI benchmarks increasingly leverage item-level statistical models, particularly item response theory (IRT), to estimate model capabilities, rank systems, select informative examples, and diagnose benchmark quality.
arXiv:2602. 09924v4 Announce Type: replace-cross Abstract: Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains challenging.
arXiv:2607. 08317v1 Announce Type: new Abstract: Modern AI models achieve strong performance on many established benchmarks, yet they still fail on tasks that humans find almost trivial, such as manipulating a string or drawing a dog with five legs.