Linxi Jiang — accepted AI-conference papers

2026

Position: Web Agents Should Use Typed Actions Instead of Click-Based Browsing

Linxi Jiang, Rui Xi, Zhijie Liu, Shuo Chen, Zhiqiang Lin, Suman Nath

ICML 2026poster

This position paper argues that building a reliable agentic web requires shifting from click-based browsing to typed actions supported by a standardized semantic layer. Today’s agents primarily operate over low-level primitives such as clicks, keystrokes, and DOM manipulation. This reliance leads to…

Cited by 0 Source ↗Scholar ↗

2026

RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments

Zeyi Liao, Jaylen Jones, Linxi Jiang, Yuting Ning, Eric Fosler-Lussier, Yu Su +2

ICLR 2026oral

Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection, where attackers embed malicious content into the environment to hijack agent behavior. Current evaluations of this threat either lack support fo…

Cited by 0 Source ↗code ↗Scholar ↗