作者位次 #14/15ACL 2026Poster· Natural Language Processing
T rajectory2 T ask: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents
Ziyi Wang · Yuxuan Lu · Yimeng Zhang · Pei Chen · Ziwei Dong · Jing Huang · Jiri Gesi · Xianfeng Tang · Chen Luo · Qun Liu · Yisi Sang · Hanqing Lu · Manling Li · Jin Lai · Dakuo Wang
摘要
Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks.In real-world applications, user requests are often (1) ambiguous, (2) changing over time, or (3...