English

Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition

Artificial Intelligence 2025-09-17 v1 Computation and Language

Abstract

Understanding user intents from UI interaction trajectories remains a challenging, yet crucial, frontier in intelligent agent development. While massive, datacenter-based, multi-modal large language models (MLLMs) possess greater capacity to handle the complexities of such sequences, smaller models which can run on-device to provide a privacy-preserving, low-cost, and low-latency user experience, struggle with accurate intent inference. We address these limitations by introducing a novel decomposed approach: first, we perform structured interaction summarization, capturing key information from each user action. Second, we perform intent extraction using a fine-tuned model operating on the aggregated summaries. This method improves intent understanding in resource-constrained models, even surpassing the base performance of large MLLMs.

Keywords

Cite

@article{arxiv.2509.12423,
  title  = {Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition},
  author = {Danielle Cohen and Yoni Halpern and Noam Kahlon and Joel Oren and Omri Berkovitch and Sapir Caduri and Ido Dagan and Anatoly Efros},
  journal= {arXiv preprint arXiv:2509.12423},
  year   = {2025}
}
R2 v1 2026-07-01T05:37:53.072Z