The End of Manual Decoding: Towards Truly End-to-End Language Models Paper • 2510.26697 • Published 19 days ago • 113
WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality Paper • 2510.18560 • Published 28 days ago • 1
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 • 91