collaborators

20 papers

math.LO2026

SOP=SOP

Artem Chernikov

The classes of SOP and SOP first-order theories coincide. This answers a question of Džamonja and Shelah from 2004.

cs.SE2026

How Reasoning Shapes Social Bias in LLM-Generated Code?

Weifeng Sun, Jieke Shi, Zhou Yang +4

Large language models (LLMs) are increasingly used for code generation, yet generated programs may exhibit social bias through unfair or differential treatment of sensitive demogra…

cs.SE2026

Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks

Chenyu Wang, Yunbo Lyu, Junda He +4

Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates. Failed runs tend to be longer a…

cs.SE2026

Bridging Behavior and Implementation: Automated Java Glue Code Generation for Behavior-Driven Development

Xinyu Shi, Zhou Yang, An Ran Chen

Behavior-Driven Development (BDD) helps technical and non-technical stakeholders share a common understanding of software requirements through natural-language scenarios. Glue code…

cs.SE2026

How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study

Yunbo Lyu, David Williams, Jieke Shi +5

The rise of Software Engineering (SE) agents, i.e., LLM-based agents that can understand large codebases and carry out engineering tasks with limited human intervention, has been m…

cs.CR2026

Watermarking LLM Agent Trajectories

Wenlong Meng, Chen Gong, Terry Yue Zhuo +6

LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial task design, high-capacity model gene…