Yuxin Wang
6 papers · 34 citations
Most-cited papers
- Relay Hindsight Experience Replay: Self-guided Continual Reinforcement Learning For Sequential Object Manipulation Tasks With Sparse Rewards2022 · 34 citations
- Test-time Scaling With Reflective Generative Model2025
- Abc-bench: Benchmarking Agentic Backend Coding In Real-world Development2026
- Terminal-bench: Benchmarking Agents On Hard, Realistic Tasks In Command Line Interfaces2026
Topics