WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
Paper • 2610.18067 • Published • 85
Esther C. Devries
Estherdevana
AI & ML interests
NLP researcher, occasional Kaggle competitor
Recent Activity
updated a dataset 15 days ago
Estherdevana/nlp-sentiment-multimodal382 published a dataset 15 days ago
Estherdevana/nlp-sentiment-multimodal382Organizations
None yet
upvoted a paper 5 days ago
upvoted 3
papers 15 days ago
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 548
Does Learning Protein Folding Generalize to Broader Reasoning?
Paper • 2609.38879 • Published • 64
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 642
upvoted a paper about 2 months ago