Towards Large Language Model-Friendly APls
Yuan Wang, Ziheng Yang, Zhanbo Wang, Mingyu Li, Zhilin Wu, Haibo Chen · ACM SIGOPS Operating Systems Review · 2025
Conventional Application Programming Interfaces (APIs) are designed for human developers. However, when Large Language Models (LLMs) act as API clients, these humancentric design choices may fail to harness the potential of LLMs, thus causing excessive overhead and task failures. We present Symphony AP1s, a class of semi-open APIs allowing LLMs to extend the API's internal logic at runtime, under the constraints of safety and controllability. Our case studies using the POSIX 'find' utility and the Robot 'PickAndPlace' API show that Symphony APIs can enable LLMs to extend API capabilities in a cost-effective and controllable manner.