Redesign Mixture-of-Experts Routers with Manifold Power Iteration Paper • 2606.12397 • Published 2 days ago • 74
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents Paper • 2606.04703 • Published 9 days ago • 22
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents Paper • 2603.14465 • Published Mar 15 • 23
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation Paper • 2602.12125 • Published Feb 12 • 67
AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research Paper • 2602.06540 • Published Feb 6 • 22