Oscar Jiang

Oscattt

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

new activity 7 days ago

Oscattt/APPL-assets:Add task_categories to metadata

authored a paper 8 days ago

Agent Priors-guided Policy Learning

View all activity

Organizations

upvoted a paper 1 day ago

Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

Paper • 2610.08215 • Published 2 days ago • 129

upvoted a paper 8 days ago

Agent Priors-guided Policy Learning

Paper • 2609.35690 • Published 12 days ago • 87

upvoted a paper about 2 months ago

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

Paper • 2608.17310 • Published Aug 18 • 110