LeWAM: End-to-End World and Action Modeling with JEPAs Paper • 2610.12818 • Published 27 days ago • 21
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight Paper • 2610.08077 • Published 29 days ago • 162
TimeBraid: Unifying Time Series and Language for Understanding and Forecasting Paper • 2609.29792 • Published Sep 24 • 18
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement Paper • 2609.39045 • Published Sep 30 • 46
UMM-Reflection Collection Learning Native Reflection in Unified Models: SFT and RL checkpoints of BAGEL-7B-MoT and the reflection-SFT data. • 3 items • Updated Sep 27 • 8
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments Paper • 2609.15364 • Published Sep 14 • 88
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism Paper • 2606.00408 • Published May 29 • 63
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction Paper • 2605.05242 • Published May 3 • 126