EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines Paper • 2601.09465 • Published Jan 14 • 42
MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences Paper • 2601.06789 • Published Jan 11 • 81
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning Paper • 2601.06943 • Published Jan 11 • 216
