Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks Paper • 2604.02795 • Published 6 days ago • 3
ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents Paper • 2604.01664 • Published 7 days ago • 8
SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale Paper • 2603.22455 • Published 16 days ago • 2