Large language models have shown remarkable ability in code generation and comprehension, yet they still struggle to reason systematically or operate effectively within real development environments. In this talk, I will share our recent efforts to move beyond static prompting toward training LLMs that can think, act, and verify like developers.

We begin by exploring how complex software issues can be decomposed into structured subtasks—planning, searching, and verifying—to teach models to perform hierarchical reasoning and adaptive decision-making. Building on this foundation, we extend the learning process to environments where models interact with external tools such as test runners, linters, and code search systems. Through this integration, models not only generate code but also validate and refine their own outputs through iterative feedback.

Together, these developments point toward a new generation of agentic LLMs—models that bridge reasoning and execution, capable of autonomously debugging, verifying, and evolving software.

I am a Principal Research Scientist at ByteDance (字节跳动). I received my PhD degree from Laboratory for Foundations of Computer Science (LFCS), The University of Edinburgh under supervision of Dr. Ajitha Rajan.

At ByteDance, I lead the Trae Research team (ByteDance Software Engineering Lab), where we conduct research on AI agents for software engineering including the application and evaluation of AI agents, and training LLMs for agents. I am also responsible for academic development and university collaboration.

I am passionate about building practical software testing, analysis, and debugging systems to predict, detect, diagnose, and fix bugs for all kinds of software systems.

Outside of work, I enjoy going to the gym.