clembench-2024: A Challenging, Dynamic, Complementary, Multilingual Benchmark and Underlying Flexible Framework for LLMs as Multi-Action Agents
Beyer, Anne and Chalamalasetti, Kranti and Hakimov, Sherzod and Madureira, Brielen and Sadler, Philipp and Schlangen, David
, 2024[PDF]
@misc{Beyer-2024,
title = {clembench-2024: A Challenging, Dynamic, Complementary, Multilingual Benchmark and Underlying Flexible Framework for LLMs as Multi-Action Agents},
author = {Beyer, Anne and Chalamalasetti, Kranti and Hakimov, Sherzod and Madureira, Brielen and Sadler, Philipp and Schlangen, David},
year = {2024},
eprint = {2405.20859},
archiveprefix = {arXiv},
primaryclass = {cs.CL}
}