← Back to People
Author of "Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Traini" on arXiv
1
Mentions
1
Articles
1
Outlets
Associated Topics
Coverage Patterns
How media typically covers Yixin Nie
Article Types
- research1
Media Angles
- technical1
Narrative Framing
- breakthrough1
Writes About
Articles
Most recent firstArticles Written
Yixin Nie as author
Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
arXivresearchneutralFeb 1, 2026
Cross-domain generalization for RL-trained LLM agents is primarily driven by state information richness and planning complexity rather than domain realism, and can be improved through strategic state randomization and step-by-step reasoning during training.
“Author of "Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Traini" on arXiv”
LLMsAI AgentsReinforcement LearningAI Research