VIGIL: Defending LLM Agents Against Tool-Stream Injection via Verify-Before-Commit

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2026 Open access

Read full text
Authors: Junda Lin, Zhaomeng Zhou, Zhi Zheng, Shuochen Liu, Tong Xu, Yong Chen, Enhong Chen
DOI: 10.18653/v1/2026.acl-long.443
Cited by: 1

Abstract

Junda Lin, Zhaomeng Zhou, Zhi Zheng, Shuochen Liu, Tong Xu, Yong Chen, Enhong Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Fields of Study & Subjects

Topic Modeling Natural Language Processing Techniques Data Quality and Management

Publication details

Journal / source
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Publisher
Association for Computational Linguistics
Pages
9764–9785
Publication date
1 January 2026