WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
This work addresses a specific bottleneck in web navigation for AI agents, offering an incremental improvement over existing methods.
The paper tackles the problem of web agents struggling to recover from errors in complex web environments by introducing an explicit rollback mechanism, resulting in improved navigation performance as demonstrated on two live web benchmarks.
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.