SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering Paper β’ 2611.13410 β’ Published 4 days ago β’ 35
Zetta ΞΆ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence Paper β’ 2608.16590 β’ Published Aug 17 β’ 141
Joint Agent Memory and Exploration Learning via Novelty Signals Paper β’ 2606.01528 β’ Published Jun 1 β’ 13
SimuWoB: Simulating Real-World Mobile Apps for Fast and Faithful GUI Agent Benchmarking Paper β’ 2605.25160 β’ Published May 24 β’ 8
UI-TARS: Pioneering Automated GUI Interaction with Native Agents Paper β’ 2501.12326 β’ Published Jan 21, 2025 β’ 65