Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence
Paper • 2608.11341 • Published • 72
🤝 Open to Collab
Zamir Bazhidi
zamirLork
AI & ML interests
AI for Science, Social Reaosning
Recent Activity
upvoted a paper about 7 hours ago
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring upvoted a paper about 7 hours ago
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement LearningOrganizations
None yet
upvoted 8
papers about 7 hours ago
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Paper • 2608.09802 • Published • 85
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Paper • 2608.05987 • Published • 104
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design
Paper • 2608.10299 • Published • 138
On-Policy Self-Distillation without Any Supervision
Paper • 2608.06296 • Published • 181
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling
Paper • 2608.15089 • Published • 449
Post-Training Leaves Behavioral Shadows on Unrelated Decisions
Paper • 2609.29233 • Published • 252
ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis
Paper • 2609.32630 • Published • 9