English

CABENCH: Benchmarking Composable AI for Solving Complex Tasks through Composing Ready-to-Use Models

Artificial Intelligence 2025-08-05 v1 Software Engineering

Abstract

Composable AI offers a scalable and effective paradigm for tackling complex AI tasks by decomposing them into sub-tasks and solving each sub-task using ready-to-use well-trained models. However, systematically evaluating methods under this setting remains largely unexplored. In this paper, we introduce CABENCH, the first public benchmark comprising 70 realistic composable AI tasks, along with a curated pool of 700 models across multiple modalities and domains. We also propose an evaluation framework to enable end-to-end assessment of composable AI solutions. To establish initial baselines, we provide human-designed reference solutions and compare their performance with two LLM-based approaches. Our results illustrate the promise of composable AI in addressing complex real-world problems while highlighting the need for methods that can fully unlock its potential by automatically generating effective execution pipelines.

Keywords

Cite

@article{arxiv.2508.02427,
  title  = {CABENCH: Benchmarking Composable AI for Solving Complex Tasks through Composing Ready-to-Use Models},
  author = {Tung-Thuy Pham and Duy-Quan Luong and Minh-Quan Duong and Trung-Hieu Nguyen and Thu-Trang Nguyen and Son Nguyen and Hieu Dinh Vo},
  journal= {arXiv preprint arXiv:2508.02427},
  year   = {2025}
}
R2 v1 2026-07-01T04:33:21.669Z