CANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG Paper • 2610.00923 • Published 14 days ago • 23
Multilingual GSM-Symbolic: What determines capability transfer across languages? Paper • 2610.03367 • Published 13 days ago • 52
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation Paper • 2609.16900 • Published 30 days ago • 49
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents Paper • 2609.17708 • Published 30 days ago • 80
Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs Paper • 2609.11499 • Published Sep 10 • 33