CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers? Paper • 2610.07557 • Published Oct 6 • 11
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published Oct 8 • 41
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published Sep 29 • 37
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem Paper • 2609.07064 • Published Sep 7 • 60