Hugging Face daily papers·5d agoAgentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads#agentic-rag#evaluation#hotpotqa
Hugging Face daily papers·8d agoInherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance#multi-agent#test-time-evolution#inherit-mas
arXiv cs.AI / cs.LG / cs.CL·12d agoOverwhelmed by Choice: Studying LLM Decision Making at Scale#llm#evaluation#decision-makingAI research
