AutoGraph-R1 Collection Directly Optimizing Knowledge Graph Construction for RAG using Reinforcement Learning • 11 items • Updated Oct 24 • 2
NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents Paper • 2510.07172 • Published Oct 8 • 28
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training Paper • 2508.00414 • Published Aug 1 • 93
From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery Paper • 2505.13259 • Published May 19 • 1