Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans Paper • 2606.10953 • Published 20 days ago • 60
The Thinking Leakage in Reinforcement Learning for LLMs Paper • 2610.14270 • Published 11 days ago • 29
Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation Paper • 2610.05076 • Published 16 days ago • 26
DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization Paper • 2608.17067 • Published Aug 17 • 23
LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know? Paper • 2605.28721 • Published May 27 • 15