Current evaluation of web agents largely reduces to binary success metrics or conformity to a single reference trajectory, ignoring the structural diversity present in benchmark datasets. We present WebGraphEval, a framework that abstracts trajectories from multiple agents into a unified, weighted action graph. This representation is directly compatible with benchmarks such as WebArena, leveraging leaderboard runs and newly collected trajectories without modifying environments. The framework canonically encodes actions, merges recurring behaviors, and applies structural analyses including reward propagation and success-weighted edge statistics. Evaluations across thousands of trajectories from six web agents show that the graph abstraction captures cross-model regularities, highlights redundancy and inefficiency, and identifies critical decision points overlooked by outcome-based metrics. By framing web interaction as graph-structured data, WebGraphEval establishes a general methodology for multi-path, cross-agent, and efficiency-aware evaluation of web agents.
@article{arxiv.2510.19205,
title = {WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph Representation},
author = {Yaoyao Qian and Yuanli Wang and Jinda Zhang and Yun Zong and Meixu Chen and Hanhan Zhou and Jindan Huang and Yifan Zeng and Xinyu Hu and Chan Hee Song and Danqing Zhang},
journal= {arXiv preprint arXiv:2510.19205},
year = {2025}
}
Comments
39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Multi-Turn Interactions in Large Language Models