WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning

ArXi:2602.12852v2 Announce Type: replace Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency remains underexplored. We observe that many state-of-the-art open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches. To address this, we propose WebClipper, a framework that compresses web agent trajectories via graph-based pruning.