WebGraphEval: Multi-Turn Trajectory Evaluation for Web Agents using Graph Representation
This provides a more nuanced evaluation methodology for web agents, addressing structural diversity in benchmarks, though it is incremental as it builds on existing frameworks without modifying environments.
The authors tackled the problem of evaluating web agents beyond binary success metrics by introducing WebGraphEval, a framework that abstracts trajectories into a weighted action graph, which captured cross-model regularities and identified inefficiencies across thousands of trajectories from six agents.
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.