Prépublication
· 2026 arXiv
EN
METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpretable units. On 228 tasks and 26 AIs, we recompute the time horizons using splines and it...
Drew T. Nguyen, William Fithian
#cs.AI
Prépublication
· 2026 arXiv
EN
Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open problem that slows p...
Artem Zholus, Nicolas Beltran-Velez et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer, a rubric, or a language-model reviewer, none of which can tell whether a new scientific model is valid. The A...
Yinling Zhang, Langchen Liu et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieval, while agentic variants adapt queries and tool use but rem...
Yilun Hao, Krishna Sayana et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh competing values. Stated-preference economics has faced this problem for decades. It judges...
Daniel Robert Kling Alexander, Catherine Louise Kling
#cs.AI
Prépublication
· 2026 arXiv
EN
Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through m...
Python Song, Zhixuan Liang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
How can we predict which base checkpoint is worth an expensive round of agentic post-training? End-to-end pass@$K$ tests whether successful behavior already appears in a base model's distribution, but it is a poor fit for agentic coding: many base checkpoints...
Tan Yu, Alexander Bukharin et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over. Through direct corpus interaction, an agent can search and read any of those files from a terminal with no indexing, and pr...
Jinheon Baek, Soyeong Jeong et al.
#cs.AI