@inproceedings{ma-etal-2026-huggingr4,
title = "{H}ugging{R}$^4$: A Progressive Reasoning Framework for Discovering Optimal Model Companions",
author = "Ma, Shaoyin and
Hu, Chenggong and
Wang, Huiqiong and
Sun, Li and
Song, Mingli and
Song, Jie",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2120/",
pages = "48219--48240",
ISBN = "979-8-89176-459-0",
abstract = "Building effective LLM agents increasingly requires selecting appropriate AI models as tools from large open repositories (*e.g.*, HuggingFace with $>$2M models) based on natural language requests. Unlike invoking a fixed set of API tools, repository-scale model selection must handle massive, evolving candidates with incomplete metadata. Existing approaches incorporate full model descriptions into prompts, resulting in prompt bloat, excessive token costs, and limited scalability. To address these issues, we propose **HuggingR$^{4}$**, the first framework to recast model selection as an iterative reasoning process rather than one-shot retrieval. By integrating **R**easoning, **R**etrieval, **R**efinement, and **R**eflection, HuggingR$^4$ progressively decomposes user intent, retrieves candidates through multi-round deliberation, refines selections via fine-grained analysis, and validates results through reflection. To facilitate rigorous evaluation, we introduce a large-scale benchmark comprising 14,399 user requests across 37 task categories. Experiments demonstrate that HuggingR$^4$ achieves 93.01{\%} workability and 84.25{\%} reasonability{---}outperforming state-of-the-art baselines by absolute margins of 17.81{\%} and 23.13{\%}, respectively, while reducing token consumption by 6.9$\times$."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2026-huggingr4">
<titleInfo>
<title>HuggingR⁴: A Progressive Reasoning Framework for Discovering Optimal Model Companions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shaoyin</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenggong</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huiqiong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingli</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Building effective LLM agents increasingly requires selecting appropriate AI models as tools from large open repositories (*e.g.*, HuggingFace with >2M models) based on natural language requests. Unlike invoking a fixed set of API tools, repository-scale model selection must handle massive, evolving candidates with incomplete metadata. Existing approaches incorporate full model descriptions into prompts, resulting in prompt bloat, excessive token costs, and limited scalability. To address these issues, we propose **HuggingR⁴**, the first framework to recast model selection as an iterative reasoning process rather than one-shot retrieval. By integrating **R**easoning, **R**etrieval, **R**efinement, and **R**eflection, HuggingR⁴ progressively decomposes user intent, retrieves candidates through multi-round deliberation, refines selections via fine-grained analysis, and validates results through reflection. To facilitate rigorous evaluation, we introduce a large-scale benchmark comprising 14,399 user requests across 37 task categories. Experiments demonstrate that HuggingR⁴ achieves 93.01% workability and 84.25% reasonability—outperforming state-of-the-art baselines by absolute margins of 17.81% and 23.13%, respectively, while reducing token consumption by 6.9\times.</abstract>
<identifier type="citekey">ma-etal-2026-huggingr4</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2120/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>48219</start>
<end>48240</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HuggingR⁴: A Progressive Reasoning Framework for Discovering Optimal Model Companions
%A Ma, Shaoyin
%A Hu, Chenggong
%A Wang, Huiqiong
%A Sun, Li
%A Song, Mingli
%A Song, Jie
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F ma-etal-2026-huggingr4
%X Building effective LLM agents increasingly requires selecting appropriate AI models as tools from large open repositories (*e.g.*, HuggingFace with >2M models) based on natural language requests. Unlike invoking a fixed set of API tools, repository-scale model selection must handle massive, evolving candidates with incomplete metadata. Existing approaches incorporate full model descriptions into prompts, resulting in prompt bloat, excessive token costs, and limited scalability. To address these issues, we propose **HuggingR⁴**, the first framework to recast model selection as an iterative reasoning process rather than one-shot retrieval. By integrating **R**easoning, **R**etrieval, **R**efinement, and **R**eflection, HuggingR⁴ progressively decomposes user intent, retrieves candidates through multi-round deliberation, refines selections via fine-grained analysis, and validates results through reflection. To facilitate rigorous evaluation, we introduce a large-scale benchmark comprising 14,399 user requests across 37 task categories. Experiments demonstrate that HuggingR⁴ achieves 93.01% workability and 84.25% reasonability—outperforming state-of-the-art baselines by absolute margins of 17.81% and 23.13%, respectively, while reducing token consumption by 6.9\times.
%U https://aclanthology.org/2026.emnlp-main.2120/
%P 48219-48240
Markdown (Informal)
[HuggingR4: A Progressive Reasoning Framework for Discovering Optimal Model Companions](https://aclanthology.org/2026.emnlp-main.2120/) (Ma et al., EMNLP 2026)
ACL