Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL Paper • 2609.20715 • Published 7 days ago • 42
HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses Paper • 2609.15938 • Published 10 days ago • 31
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published 17 days ago • 372
A Common Measure of Communication for Speech Brain-Computer Interfaces Paper • 2609.02887 • Published 22 days ago • 10
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published 21 days ago • 186
Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing Paper • 2608.11660 • Published Aug 12 • 11
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 265
Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation Paper • 2608.05785 • Published Aug 6 • 11
When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills Paper • 2608.03700 • Published Aug 4 • 9
DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents Paper • 2608.01827 • Published Aug 3 • 19