11 citations · 41 across the 26 of their papers we have counts for
3 papers · 1 filter
FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks
Jun Takahashi, Atsunori Moteki, Akiyoshi Uchida +11
This paper introduces FieldWorkArena, a benchmark for agentic AI targeting real-world field work. With the recent increase in demand for agentic AI, they are built to detect and do…
Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale
Tianyue Ou, Frank F. Xu, Aman Madaan +7
LLMs can now act as autonomous agents that interact with digital environments and complete specific objectives (e.g., arranging an online meeting). However, accuracy is still far f…
Program-Aided Reasoners (better) Know What They Know
Anubha Kabra, Sanketh Rangreji, Yash Mathur +3
Prior work shows that program-aided reasoning, in which large language models (LLMs) are combined with programs written in programming languages such as Python, can significantly i…