HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published Sep 1 • 568
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution Paper • 2608.25593 • Published Aug 26 • 69
StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding Paper • 2608.05703 • Published Aug 6 • 17
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning Paper • 2608.02585 • Published Aug 3 • 25
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model Paper • 2607.11643 • Published Jul 13 • 43
A Sparse and Truncated State Vector Simulator for Peaked Circuits Paper • 2607.07816 • Published Jul 8 • 7
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Paper • 2607.02255 • Published Jul 2 • 69