Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering
Paper • 2605.29648 • Published • 6
02. Prompt engineering
-
-
Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
Paper • 2605.29548 • Published • 5 -
Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation
Paper • 2605.29861 • Published • 10 -
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
Paper • 2605.31264 • Published • 68 -
dMoE: dLLMs with Learnable Block Experts
Paper • 2605.30876 • Published • 19