DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
Paper • 2609.04094 • Published • 23
Dinesh Khandelwal
dineshkh
·
AI & ML interests
LLM, Deep Learning
Recent Activity
upvoted a paper about 17 hours ago
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training upvoted a paper over 1 year ago
Selective Self-to-Supervised Fine-Tuning for Generalization in Large
Language ModelsOrganizations
