# HuggingR4: A Progressive Reasoning Framework for Discovering Optimal Model Companions

arXiv: https://arxiv.org/abs/2511.18715 · HTML: https://mlsanity.com/paper/2511.18715/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 20 of 20)

- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Multi-agent Architecture Search via Agentic Supernet](https://mlsanity.com/paper/2502.04180/) (2025)
- [BERT: A Review of Applications in Natural Language Processing and Understanding](https://mlsanity.com/paper/2103.11943/) (2021)
- [Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools](https://mlsanity.com/paper/2502.04644/) (2025)
- [A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)](https://mlsanity.com/paper/2505.02279/) (2025)
- [Boosting Language Models Reasoning with Chain-of-Knowledge Prompting](https://mlsanity.com/paper/2306.06427/) (2023)
- [ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents](https://mlsanity.com/paper/2505.06416/) (2025)
- [Automatic Model Selection with Large Language Models for Reasoning](https://mlsanity.com/paper/2305.14333/) (2023)
- [Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2505.11277/) (2025)
- [RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.03275/) (2025)
- [Optimizing Language Model's Reasoning Abilities with Weak Supervision](https://mlsanity.com/paper/2405.04086/) (2024)
- [From REST to MCP: An Empirical Study of API Wrapping and Automated Server Generation for LLM Agents](https://mlsanity.com/paper/2507.16044/) (2025)
- [MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol Servers](https://mlsanity.com/paper/2504.08999/) (2025)
- [Multimodal Benchmarking and Recommendation of Text-to-Image Generation Models](https://mlsanity.com/paper/2505.04650/) (2025)
- [Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate](https://mlsanity.com/paper/2505.10870/) (2025)
- [You Only Submit One Image to Find the Most Suitable Generative Model](https://mlsanity.com/paper/2412.12232/) (2024)
- [Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning](https://mlsanity.com/paper/2505.22591/) (2025)
- [Adaptive Selection of Deep Learning Models on Embedded Systems](https://mlsanity.com/paper/1805.04252/) (2018)

## Abstract (arXiv)

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 synergistically integrating Reasoning, Retrieval, Refinement, and Reflection, 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 diverse user requests across 37 task categories. Experiments demonstrate that HuggingR4 achieves 92.03% workability and 82.46% reasonability-outperforming current state-of-the-art baselines by 26.51% and 33.25%, respectively, while reducing token consumption by 6.9 ×.