作者位次 #5/6ACL 2026Poster· Natural Language Processing
ALDEN : Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents
Tianyu Yang · Terry Ruas · Yijun Tian · Jan Philip Wahle · Daniel Kurzawe · Bela Gipp
摘要
While Vision–language models (VLMs) interpret text-rich images effectively, they struggle with reasoning across long, multi-page documents. We present \textbf{A} ctive \mathbf{L} ong \mathbf{D} ocum \mathbf{E} nt \mathbf{N} avigation (ALDEN), a multi-turn reinforcement learning framework that fin...