Graham Neubig
3 papers · Latest:
Machine Learning
Recursive Agent Optimization
Recursive Agent Optimization (RAO) trains agents to recursively delegate sub-tasks, enabling them to scale and generalize more effectively.
2605.06639
Software EngineeringAsking What Matters: Reward-Driven Clarification for Software Engineering Tasks
CLARITI, an 8B module, uses reward-driven clarification for software engineering tasks, matching GPT-5's resolution with 41% fewer questions.
2604.14624
Natural Language ProcessingWhat do Language Models Learn and When? The Implicit Curriculum Hypothesis
LLMs acquire skills during pretraining in a consistent, compositional order, predictable across models and data, revealing a structured learning curriculum.
2604.08510
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.