False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 4 days ago • 336
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 5 days ago • 418
EvoOntology: A Self-Evolving Ontology Layer for Data Agents Paper • 2609.15779 • Published 20 days ago • 159
FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis Paper • 2608.18580 • Published Aug 19 • 96
Running Featured 853 Agent Memory Leaderboard 🧠 853 Unified memory evaluation · Results expected August 12.