This work builds a minimal multi-agent harness from the ground up and traces this frontier by varying, one at a time, the workflow stage at which a lead delegates to its workers (planning, implementation, or verification), the models that form the team, and the number of workers.
Keenan Samway, Daniel D'Souza, Omar Darwiche Domingues et al.· 0 citations
CIRCLE operationalizes the Validation phase of TEVV by translating priorities of stakeholders outside the stack into measurable signals, and produces systematic knowledge that can enable governance based on materialized downstream effects rather than theoretical capabilities.
Reva Schwartz, Carina E. I. Westling, Morgan Briggs et al.· arXiv.org· 1 citation· ⚡1
It is shown the path to generalizing L2 reasoning to held-out languages goes through broader language coverage, readily available multilingual non-reasoning data, and a sufficient English reasoning backbone, indicating that reasoning is a language-agnostic behavior that can be transferred across typologically diverse l...
Mehrnaz Mofakhami, Ananya Sahu, Alejandro R. Salamanca et al.· 0 citations
The IOL-AI Challenge is presented, an open-science competition run on the unseen problems of the International Linguistics Olympiad 2026 Individual Contest, evaluated both automatically and, for the first time, by members of the official IOL Jury under the same rubrics applied to human contestants.
Eduardo Sánchez, Rita Berrada, Dan-Mircea Mirea et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.