WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms

Zhisong Zhang, Tianqing Fang, Kaixin Ma, Wenhao Yu, Hongming Zhang, Haitao Mi, Dong Yu


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 models 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.
Anthology ID:
2026.eacl-short.12
Volume:
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Vera Demberg, Kentaro Inui, Lluís Marquez
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
187–197
Language:
URL:
https://preview.aclanthology.org/ingest-eacl/2026.eacl-short.12/
DOI:
Bibkey:
Cite (ACL):
Zhisong Zhang, Tianqing Fang, Kaixin Ma, Wenhao Yu, Hongming Zhang, Haitao Mi, and Dong Yu. 2026. WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 187–197, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms (Zhang et al., EACL 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-eacl/2026.eacl-short.12.pdf
Checklist:
 2026.eacl-short.12.checklist.pdf