Stable ToolBench
Emerging5papers using it
2025first seen
The 'Stable ToolBench' is a dataset/benchmark that contains a collection of tools and their functionalities used to evaluate the performance of large language models in tool calling and interaction with executable interfaces.
Papers using Stable ToolBench (5)
- ParaTool: Shifting Tool Representations from Context to ParametersCodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process SupervisionSelf-Improving World Modelling with Latent ActionsMIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool LearningStableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of
7,000+ Real-World APIs