LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets Paper • 2610.09872 • Published 25 days ago • 58
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Paper • 2610.06100 • Published 27 days ago • 74
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 226
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published Sep 29 • 203
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers Paper • 2609.01343 • Published Sep 1 • 90