DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
Paper • 2609.04094 • Published • 26
Kiran Kate
kirankate06
AI & ML interests
None yet
Recent Activity
upvoted an article about 2 months ago
Model Routing Is Simple. Until It Isn’t. upvoted an article about 2 months ago
How Much Memory Does Your Agent Actually Need?Organizations
None yet
upvoted a paper 30 days ago
upvoted 3
articles about 2 months ago
Article
Model Routing Is Simple. Until It Isn’t.
ibm-research
• • 93 Article
How Much Memory Does Your Agent Actually Need?
ibm-research
• • 83 Article
Thinking of ACE? We Can Do It with Fewer Tokens
ibm-research
• • 33 upvoted an article 3 months ago
Article
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
ibm-research
• • 40 upvoted an article 4 months ago
Article
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
ibm-research
• • 92 upvoted a paper 5 months ago
upvoted an article 7 months ago
Article
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
LinkedIn
• • 82 upvoted an article 10 months ago
Article
CUGA on Hugging Face: Democratizing Configurable AI Agents
ibm-research
• • 68