# You're Hired: Strategic Model Selection for LLM Collaboration

arXiv: https://arxiv.org/abs/2609.38816 · HTML: https://mlsanity.com/paper/2609.38816/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 34 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Are We Done with MMLU?](https://mlsanity.com/paper/2406.04127/) (2024)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents](https://mlsanity.com/paper/2408.07060/) (2024)
- [Idiosyncrasies in Large Language Models](https://mlsanity.com/paper/2502.12150/) (2025)
- [When One LLM Drools, Multi-LLM Collaboration Rules](https://mlsanity.com/paper/2502.04506/) (2025)
- [Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks](https://mlsanity.com/paper/2406.08598/) (2024)
- [Learning Compact Representations of LLM Abilities via Item Response Theory](https://mlsanity.com/paper/2510.00844/) (2025)
- [SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat](https://mlsanity.com/paper/2506.04721/) (2025)
- [Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems](https://mlsanity.com/paper/2602.05176/) (2026)
- [Model Selection with Model Zoo via Graph Learning](https://mlsanity.com/paper/2404.03988/) (2024)
- [LLM Chemistry Estimation for Multi-LLM Recommendation](https://mlsanity.com/paper/2510.03930/) (2025)
- [Scaling Participation in Modular AI Systems](https://mlsanity.com/paper/2606.07812/) (2026)

## Abstract (arXiv)

While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems remain bottlenecked on pre-defined and hand-crafted model pools. In this work, we investigate the problem of model selection in multi-LLM systems. We propose and systematically evaluate a taxonomy of 9 selection algorithms ranging from diversity of model descriptions, capability-aware behavioral diversity, and LLM-based recruiters. We conduct extensive experiments across two candidate pools of 10 and 32 models, deployed in four model collaboration algorithms, and evaluated across tasks spanning math, coding, QA, and reasoning. Results demonstrate that successful selection algorithms greatly outperform random or heuristics-based teams such as merely selecting the models with top individual performance, by up to 36.1% across settings. Specifically, capability- and training-based selection strategies alleviate selection variance and achieve the best performance, which we recommend to employ before deploying real-world multi-LLM systems. Further analysis reveals that larger candidate pools pose greater challenges to shallow selection heuristics, while algorithms grounded in interacting with candidate models and understanding model capability robustly filter out misaligned, unsafe models, as well as generalizing to novel, out-of-distribution tasks. Together, we establish that principled and informed team selection is critical and present strong model selection algorithms for assembling effective multi-LLM systems.