AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 65
Julian Schaefer
julianscha
AI & ML interests
prompt engineering
Recent Activity
upvoted a paper about 5 hours ago
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks upvoted a paper about 5 hours ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents upvoted a paper about 5 hours ago
MaLiang-Harness: A Programmable Path to Image and Video GenerationOrganizations
None yet
upvoted 4
papers about 5 hours ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 92
MaLiang-Harness: A Programmable Path to Image and Video Generation
Paper • 2609.34309 • Published • 384
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 205