DecepEval: A Benchmark for Evaluating Deception in LLM Agents Paper • 2610.07967 • Published 20 days ago • 61
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 27 days ago • 208
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 26 days ago • 235
VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction Paper • 2608.26005 • Published Aug 26 • 140
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published Aug 26 • 486