@article{battleagentbenchabenchmarkforevaluating, title = {BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems}, author = {Wei Wang and Dan Zhang and Tao Feng and Boyan Wang and Jie Tang}, year = {2024}, eprint = {2408.15971}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.15971v1}, }