Tao Gui

发表论文 206 篇 · 总被引 9047 次 · h-index 42

代表论文

• AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning (2025 · arXiv.org · 被引 67)
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping (2025 · arXiv.org · 被引 51)
• CL-bench: A Benchmark for Context Learning (2026 · arXiv.org · 被引 45)
• Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026 · Computer Science Review · 被引 20)
• OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026 · Annual Meeting of the Association for Computational Linguistics · 被引 16)
• MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning (2025 · arXiv.org · 被引 16)