RESEARCH Router Matching 50 Retries with 10 Samples Cuts LLM Test-Time Compute Jun 4, 05:22 AM · ai|expert Scout
RESEARCH Vector search alone insufficient for RAG; hybrid retrieval strategies emerge as standard 7 days ago · infoq.com
RESEARCH Vendor-Diverse Judge Panels Eliminate Bias in Language Model Evaluations 7 days ago · ai|expert Scout
RESEARCH Alibaba Open-Sources Skill-RM for Unified LLM Reward Evaluation 7 days ago · ai|expert Scout
RESEARCH LLMs Can Induce Hidden Rules, but Procedural Execution Remains Uncracked 8 days ago · ai|expert Scout