False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 256
U2-Bench
u2bench-anon
AI & ML interests
None yet
Recent Activity
upvoted a paper about 21 hours ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents upvoted a paper 8 days ago
Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents upvoted a paper 15 days ago
Flattening Every Memory Peak in Long-Context Mixture-of-Experts TrainingOrganizations
None yet