DEFT: Demystifying VLN Failures via a Unified Dual-View Explainability Framework for LLM-based Agents

This paper presents DEFT, a unified dual-view explainability framework for understanding failure modes in LLM-based VLN agents.

Recommended citation: Yawen Wang, Yihan Dai, Jianming Chen, Junjie Wang, and Qing Wang. (2026). "DEFT: Demystifying VLN Failures via a Unified Dual-View Explainability Framework for LLM-based Agents." ACL 2026.
Download Paper