# AutoMix: Automatically Mixing Language Models

arXiv: https://arxiv.org/abs/2310.12963 · HTML: https://mlsanity.com/paper/2310.12963/

## Key facts

- Cited by 125 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 69 references that are in the map.
- First posted on arXiv 19 Oct 2023.

## Builds on (most cited first, 30 of 45)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Faith and Fate: Limits of Transformers on Compositionality](https://mlsanity.com/paper/2305.18654/) (2023)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [Confident Adaptive Language Modeling](https://mlsanity.com/paper/2207.07061/) (2022)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [FastBERT: a Self-distilling BERT with Adaptive Inference Time](https://mlsanity.com/paper/2004.02178/) (2020)
- [QuALITY: Question Answering with Long Input Texts, Yes!](https://mlsanity.com/paper/2112.08608/) (2021)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [Reframing Instructional Prompts to GPTk's Language](https://mlsanity.com/paper/2109.07830/) (2021)

## Built on by (most cited first, 30 of 125)

- [RouterBench: A Benchmark for Multi-LLM Routing System](https://mlsanity.com/paper/2403.12031/) (2024)
- [Universal Model Routing for Efficient LLM Inference](https://mlsanity.com/paper/2502.08773/) (2025)
- [Harnessing Multiple Large Language Models: A Survey on LLM Ensemble](https://mlsanity.com/paper/2502.18036/) (2025)
- [A Unified Approach to Routing and Cascading for LLMs](https://mlsanity.com/paper/2410.10347/) (2024)
- [What is the Role of Small Models in the LLM Era: A Survey](https://mlsanity.com/paper/2409.06857/) (2024)
- [Cost-Effective Online Multi-LLM Selection with Versatile Reward Models](https://mlsanity.com/paper/2405.16587/) (2024)
- [CARROT: A Cost Aware Rate Optimal Router](https://mlsanity.com/paper/2502.03261/) (2025)
- [Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection](https://mlsanity.com/paper/2405.02134/) (2024)
- [Prompt-to-Leaderboard](https://mlsanity.com/paper/2502.14855/) (2025)
- [Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems](https://mlsanity.com/paper/2502.00409/) (2025)
- [Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution](https://mlsanity.com/paper/2506.17670/) (2025)
- [Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey](https://mlsanity.com/paper/2603.04445/) (2026)
- [Cost-Aware Contrastive Routing for LLMs](https://mlsanity.com/paper/2508.12491/) (2025)
- [Cost-Saving LLM Cascades with Early Abstention](https://mlsanity.com/paper/2502.09054/) (2025)
- [R2-Router: A New Paradigm for LLM Routing with Reasoning](https://mlsanity.com/paper/2602.02823/) (2026)
- [PickLLM: Context-Aware RL-Assisted Large Language Model Routing](https://mlsanity.com/paper/2412.12170/) (2024)
- [Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving](https://mlsanity.com/paper/2509.02718/) (2025)
- [MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing](https://mlsanity.com/paper/2601.17814/) (2026)
- [When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models](https://mlsanity.com/paper/2606.27288/) (2026)
- [Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models](https://mlsanity.com/paper/2506.00911/) (2025)
- [Life-Cycle Routing Vulnerabilities of LLM Router](https://mlsanity.com/paper/2503.08704/) (2025)
- [Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers](https://mlsanity.com/paper/2505.12601/) (2025)
- [Cascaded Language Models for Cost-effective Human-AI Decision-Making](https://mlsanity.com/paper/2506.11887/) (2025)
- [SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks](https://mlsanity.com/paper/2607.00053/) (2026)
- [Rational Tuning of LLM Cascades via Probabilistic Modeling](https://mlsanity.com/paper/2501.09345/) (2025)
- [When Routing Collapses: On the Degenerate Convergence of LLM Routers](https://mlsanity.com/paper/2602.03478/) (2026)
- [Agent-as-a-Router: Agentic Model Routing for Coding Tasks](https://mlsanity.com/paper/2606.22902/) (2026)
- [MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees](https://mlsanity.com/paper/2505.19947/) (2025)
- [TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks](https://mlsanity.com/paper/2601.10245/) (2026)
- [Adaptive Vision-Language Model Routing for Computer Use Agents](https://mlsanity.com/paper/2603.12823/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are now available from cloud API providers in various sizes and configurations. While this diversity offers a broad spectrum of choices, effectively leveraging the options to optimize computational cost and performance remains challenging. In this work, we present Automix, an approach that strategically routes queries to larger LMs, based on the approximate correctness of outputs from a smaller LM. Central to Automix are two key technical contributions. First, it has a few-shot self-verification mechanism, which estimates the reliability of its own outputs without requiring extensive training. Second, given that self-verification can be noisy, it employs a POMDP based router that can effectively select an appropriately sized model, based on answer confidence. Experiments across five language models and five challenging datasets show that Automix consistently surpasses strong baselines, reducing computational cost by over 50% for comparable performance.