AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security Paper • 2601.18491 • Published 8 days ago • 121
Controlled Self-Evolution for Algorithmic Code Optimization Paper • 2601.07348 • Published 22 days ago • 114
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning Paper • 2601.06943 • Published 23 days ago • 209
Controlled Self-Evolution for Algorithmic Code Optimization Paper • 2601.07348 • Published 22 days ago • 114
MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences Paper • 2601.06789 • Published 23 days ago • 78
KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions Paper • 2601.04745 • Published 26 days ago • 57
Running 3.67k The Ultra-Scale Playbook 🌌 3.67k The ultimate guide to training LLM on large GPU Clusters