BiFE: Search-Efficient Discovery of CPU-Only Branching Policies via LLM-based Bi-Fidelity EvolutionResearchSep 30, 2026
Can AI Scientists Change Their Minds? Prior-Evidence Conflict in Synthetic UniversesResearchSep 30, 2026
A theoretical model of dynamical grammatical gender shifting based on set-valued set functionResearchSep 30, 2026
How Strong Is the Evidence for the Artificial Hivemind? Reevaluating Evidence for the Open-Ended Homogeneity of Language ModelsResearchSep 30, 2026
SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language ModelsResearchSep 30, 2026
Distinguish or Homogenize: Last-Chance Policy Identification and Risk-Budgeted Recovery under Irreversible Resource DepletionResearchSep 30, 2026
Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward ModelsResearchSep 30, 2026