DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment Paper • 2607.07820 • Published 28 days ago • 91
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps Paper • 2605.16928 • Published May 16 • 99
XSkill: Continual Learning from Experience and Skills in Multimodal Agents Paper • 2603.12056 • Published Jul 1 • 34
AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios Paper • 2602.23166 • Published Feb 26 • 45
AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning Paper • 2510.06261 • Published Oct 5, 2025 • 6