Interfaze: The Future of AI is built on Task-Specific Small Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khurdula, Harsha Vardhan, Agarwal, Vineet, Khemlani, Yoeven D
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911421073195008
author Khurdula, Harsha Vardhan
Agarwal, Vineet
Khemlani, Yoeven D
author_facet Khurdula, Harsha Vardhan
Agarwal, Vineet
Khemlani, Yoeven D
contents We present Interfaze, a system that treats modern LLM applications as a problem of building and acting over context, not just picking the right monolithic model. Instead of a single transformer, we combine (i) a stack of heterogeneous DNNs paired with small language models as perception modules for OCR involving complex PDFs, charts and diagrams, and multilingual ASR with (ii) a context-construction layer that crawls, indexes, and parses external sources (web pages, code, PDFs) into compact structured state, and (iii) an action layer that can browse, retrieve, execute code in a sandbox, and drive a headless browser for dynamic web pages. A thin controller sits on top of this stack and exposes a single, OpenAI-style endpoint: it decides which small models and actions to run and always forwards the distilled context to a user-selected LLM that produces the final response. On this architecture, Interfaze-Beta achieves 83.6% on MMLU-Pro, 91.4% on MMLU, 81.3% on GPQA-Diamond, 57.8% on LiveCodeBench v5, and 90.0% on AIME-2025, along with strong multimodal scores on MMMU (val) (77.3%), AI2D (91.5%), ChartQA (90.9%), and Common Voice v16 (90.8%). We show that most queries are handled primarily by the small-model and tool stack, with the large LLM operating only on distilled context, yielding competitive accuracy while shifting the bulk of computation away from the most expensive and monolithic models.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04101
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Interfaze: The Future of AI is built on Task-Specific Small Models
Khurdula, Harsha Vardhan
Agarwal, Vineet
Khemlani, Yoeven D
Artificial Intelligence
We present Interfaze, a system that treats modern LLM applications as a problem of building and acting over context, not just picking the right monolithic model. Instead of a single transformer, we combine (i) a stack of heterogeneous DNNs paired with small language models as perception modules for OCR involving complex PDFs, charts and diagrams, and multilingual ASR with (ii) a context-construction layer that crawls, indexes, and parses external sources (web pages, code, PDFs) into compact structured state, and (iii) an action layer that can browse, retrieve, execute code in a sandbox, and drive a headless browser for dynamic web pages. A thin controller sits on top of this stack and exposes a single, OpenAI-style endpoint: it decides which small models and actions to run and always forwards the distilled context to a user-selected LLM that produces the final response. On this architecture, Interfaze-Beta achieves 83.6% on MMLU-Pro, 91.4% on MMLU, 81.3% on GPQA-Diamond, 57.8% on LiveCodeBench v5, and 90.0% on AIME-2025, along with strong multimodal scores on MMMU (val) (77.3%), AI2D (91.5%), ChartQA (90.9%), and Common Voice v16 (90.8%). We show that most queries are handled primarily by the small-model and tool stack, with the large LLM operating only on distilled context, yielding competitive accuracy while shifting the bulk of computation away from the most expensive and monolithic models.
title Interfaze: The Future of AI is built on Task-Specific Small Models
topic Artificial Intelligence
url https://arxiv.org/abs/2602.04101