Jiahang Xu
Source-listed: Research Software Development Engineer · Microsoft Research Asia (Microsoft Research)
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Agent Lightning v1.0: Towards Harnessed Agentic RLSaved credit: Contributor · 2026Explore people connected to this work →
- From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent OptimizationSaved credit: Contributor · 2026Explore people connected to this work →
- What are Key Factors for Updates in RL for LLM Reasoning?Saved credit: Contributor · 2026Explore people connected to this work →
- Mutual Reasoning Makes Smaller LLMs Stronger Problem-SolversSaved credit: First author · 2024Explore people connected to this work →
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your PhoneSaved credit: Contributor · 2024Explore people connected to this work →