AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Paper • 2607.02255 • Published 7 days ago • 60
Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agents Paper • 2606.22207 • Published 18 days ago • 4
Learning from the Self-future: On-policy Self-distillation for dLLMs Paper • 2606.18195 • Published 23 days ago • 76
When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models Paper • 2605.28181 • Published May 27 • 3
Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design Paper • 2605.15871 • Published May 15 • 17
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization Paper • 2605.17757 • Published May 18 • 66
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining Paper • 2605.14747 • Published May 14 • 147