Agent

From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements
Coding agents can generate web applications from natural-language descriptions, yet a recent benchmark study shows that generated …
Yuxuan Wan, Tingshuo Liang, Alex Jiakai XU, Jingyu Xiao, Yintong Huo, Michael R. Lyu
Project DOI
An Approach for Systematic Decomposition of Complex LLM Tasks
Large Language Models (LLMs) suffer from reliability issues on complex tasks, as existing decomposition methods are heuristic and rely …
Tianle Zhou, Alex Jiakai XU, Guanhong Liu, Jiaxiang Liu, Haonan Wang, Eugene Wu
DOI
Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development
Developing full-stack web applications is complex and time-intensive, demanding proficiency across diverse technologies and frameworks. …
Yuxuan Wan, Tingshuo Liang, Alex Jiakai XU, Jingyu Xiao, Yintong Huo, Michael R. Lyu
Project DOI
Toward Systems Foundations for Agentic Exploration
This paper presents a systems perspective on the challenges of supporting agentic exploration in LLM-powered agents, focusing on fork semantics, external side-effects, and native forking.
Alex Jiakai XU, Tianle Zhou, Eugene Wu, Kostis Kaffes
Cite Project DOI
Toward Systems Foundations for Agentic Exploration
TDDev
Multi-agent test-driven development framework that generates full-stack web applications from requirements by converting requirements into tests, validating deployed apps through browser interactions, and iteratively repairing failures.
Poster
TDDev