@article{towardsreliablebenchmarkingacontaminatio, title = {Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling}, author = {Seiji Maekawa and Jackson Hassell and Pouya Pezeshkpour and Tom Mitchell and Estevam Hruschka}, year = {2025}, eprint = {2509.26553}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.26553}, }