作者位次 #2/5ACL 2026Findings· Findings of ACL
Towards Preference Following in Tool Calling Language Agents
Zhi-Yuan Chen · Siyu Lu · Qianlong Xie · Xingxing Wang · Yankai Lin
摘要
Large language model (LLM)-based agents have demonstrated remarkable capabilities in tool use, but their ability to follow user preferences when calling tools remains underexplored. To address this gap, we introduce APOLLO, a benchmark designed to evaluate agents’ ability to identify personalized...