collaborators

13 papers

cs.SE2026

When Agents Do Not Stop: Uncovering Infinite Agentic Loops in LLM Agents

Xinyi Hou, Shenao Wang, Yanjie Zhao +1

LLM agents increasingly rely on iterative execution to solve tasks through planning, tool use, state updates, and agent collaboration. While this design enables flexible automation…

cs.SE2026

AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs

Shenao Wang, Xinyi Hou, Yanjie Zhao +2

LLM agents are increasingly developed as source-code applications built on agent frameworks. These agent programs combine conventional host-language code with framework-defined sem…

cs.SE2026

LaQual: An Automated Framework for LLM App Quality Evaluation

Yan Wang, Xinyi Hou, Junjun Si +3

Representing a new paradigm in software distribution, LLM app stores are rapidly emerging, offering users diverse choices for content generation, coding assistance, education, and…

cs.SE2026

Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem

Xinyi Hou, Yanjie Zhao, Haoyu Wang

Model Context Protocol (MCP) have quickly become the interface layer between LLM agents and external tools, yet they also introduce unsafe data flows that existing analyzers handle…

cs.CR2026

Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions

Shenao Wang, Xinyi Hou, Zhao Liu +5

GitHub Actions is increasingly used to deploy LLM-based agents for repository-centric tasks such as issue triage, pull-request review, code modification, and release assistance. Th…

cs.SE2026

CommitSuite: A Comprehensive Benchmark for Commit Classification and Message Generation

Zirui Wan, Zhaonan Wu, Xinyi Hou +3

High-quality commit messages are critical for maintaining software projects, yet ensuring their consistency and informativeness remains a practical challenge. While the Conventiona…