HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone Paper • 2607.25895 • Published 8 days ago • 152
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation Paper • 2607.24720 • Published 9 days ago • 26
Weak-to-Strong Generalization via Direct On-Policy Distillation Paper • 2607.05394 • Published 28 days ago • 139
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application Paper • 2606.12191 • Published Jun 10 • 71
DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios Paper • 2604.25914 • Published Apr 28 • 42
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents Paper • 2604.23781 • Published Apr 26 • 33
From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space Paper • 2604.14142 • Published Apr 15 • 30