Enhancing Web Agents with Explicit Rollback Mechanisms

ACL ARR 2025 May Submission620 Authors

Abstract: With recent advancements in large language models, web agents have been greatly improved. However, dealing with complex and dynamic web environments requires more advanced planning and search abilities. Previous studies usually adopt a greedy one-way search strategy, which may struggle to recover from erroneous states. In this work, we enhance web agents with an explicit rollback mechanism, enabling the agent to revert back to a previous state in its navigation trajectory. This mechanism gives the model the flexibility to directly control the search process, leading to an effective and efficient web navigation method. We conduct experiments on two live web navigation benchmarks with zero-shot and fine-tuning settings. The results demonstrate the effectiveness of our proposed approach.

Paper Type: Short

Research Area: Language Modeling

Research Area Keywords: web agent, rollback mechanism

Contribution Types: NLP engineering experiment

Languages Studied: English

Keywords: web agent, rollback mechanism

Submission Number: 620