ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario
This work addresses the need for better evaluation of LLMs' function calling in complex, long-context scenarios, which is incremental as it builds on existing benchmarks by adding multi-step and constrained elements.
The authors tackled the problem of evaluating large language models' function calling abilities in complex real-world scenarios by introducing ComplexFuncBench, a benchmark covering multi-step and constrained function calling with 128k long context, and found that state-of-the-art LLMs show deficiencies in these tasks.
Enhancing large language models (LLMs) with real-time APIs can help generate more accurate and up-to-date responses. However, evaluating the function calling abilities of LLMs in real-world scenarios remains under-explored due to the complexity of data collection and evaluation. In this work, we introduce ComplexFuncBench, a benchmark for complex function calling across five real-world scenarios. Compared to existing benchmarks, ComplexFuncBench encompasses multi-step and constrained function calling, which requires long-parameter filing, parameter value reasoning, and 128k long context. Additionally, we propose an automatic framework, ComplexEval, for quantitatively evaluating complex function calling tasks. Through comprehensive experiments, we demonstrate the deficiencies of state-of-the-art LLMs in function calling and suggest future directions for optimizing these capabilities. The data and code are available at \url{https://github.com/THUDM/ComplexFuncBench}.