StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs
This work addresses the problem of realistic and stable tool learning benchmarks for researchers and developers in AI, though it appears incremental as it builds on existing tool learning frameworks.
The paper tackled the challenge of balancing stability, scalability, and realness in tool environments for LLMs by proposing MirrorAPI, a framework that trains specialized LLMs to simulate real API responses, achieving superior accuracy and stability compared to state-of-the-art methods.
The rapid advancement of large language models (LLMs) has spurred significant interest in tool learning, where LLMs are augmented with external tools to tackle complex tasks. However, existing tool environments face challenges in balancing stability, scalability, and realness, particularly for benchmarking purposes. To address this problem, we propose MirrorAPI, a novel framework that trains specialized LLMs to accurately simulate real API responses, effectively acting as "mirrors" to tool environments. Using a comprehensive dataset of request-response pairs from 7,000+ APIs, we employ supervised fine-tuning and chain-of-thought reasoning to enhance simulation fidelity. MirrorAPI achieves superior accuracy and stability compared to state-of-the-art methods, as demonstrated by its performance on the newly constructed MirrorAPI-Bench and its integration into StableToolBench.