Skyler Hallinan Thejas Venkatesh Xiang Ren 0001 Sai Praneeth Karimireddy Ashwin Paranjape Yuhao Zhang 0004 Jack Hessel OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction. 620-638 2026 CAIS https://doi.org/10.1145/3786335.3813182 conf/cais/2026 db/conf/cais/cais2026.html#HallinanVRKPZH26