CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers? Paper • 2610.07557 • Published 8 days ago • 73
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published 6 days ago • 153
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 15 days ago • 131