Leonardo Souza

leonardosouza's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers 8 days ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 14 days ago • 557

Does Learning Protein Folding Generalize to Broader Reasoning?

Paper • 2609.38879 • Published 13 days ago • 63

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Paper • 2609.39102 • Published 13 days ago • 653

upvoted a paper about 1 month ago

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published Sep 1 • 568