WebCoEvo: Adversarial Co-Evolution for Web Agents
Computer-use Agents · Adaptation
University of Michigan · Mar – Jun 2026
Advisor: Prof. Honglak Lee
I developed WebCoEvo, an adversarial co-evolution framework that helped web agents adapt to changing websites by learning generalizable reflection rules from their failures.
My contributions
- Paired a coding-agent-driven website version generator with a web agent to study adaptation to evolving interfaces.
- Extracted generalizable meta-level reflection rules from agent failure modes, improving performance by 19.6% over an ExpeL baseline.
- Worked on a knowledge-graph pipeline to automatically identify tasks affected by website version changes.
- Containerized multiple website versions with Docker using BrowserGym and AgentLab.