Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models Paper • 2609.37568 • Published Sep 29 • 5
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs Paper • 2609.32259 • Published Sep 29 • 27
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop Paper • 2610.00559 • Published Sep 30 • 35
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization Paper • 2610.00906 • Published Oct 1 • 60