# Scaling LLM Inference with Optimized Sample Compute Allocation

arXiv: https://arxiv.org/abs/2410.22480 · HTML: https://mlsanity.com/paper/2410.22480/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 29 Oct 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 23 of 23)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [HyperTree Proof Search for Neural Theorem Proving](https://mlsanity.com/paper/2205.11491/) (2022)
- [From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models](https://mlsanity.com/paper/2406.16838/) (2024)
- [Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing](https://mlsanity.com/paper/2404.12253/) (2024)
- [Language Model Cascades](https://mlsanity.com/paper/2207.10342/) (2022)
- [Learning How Hard to Think: Input-Adaptive Allocation of LM Computation](https://mlsanity.com/paper/2410.04707/) (2024)
- [Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency](https://mlsanity.com/paper/2309.17272/) (2023)
- [ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers](https://mlsanity.com/paper/2305.14591/) (2023)
- [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://mlsanity.com/paper/2303.04673/) (2023)
- [THOUGHTSCULPT: Reasoning with Intermediate Revision and Search](https://mlsanity.com/paper/2404.05966/) (2024)
- [LLM can Achieve Self-Regulation via Hyperparameter Aware Generation](https://mlsanity.com/paper/2402.11251/) (2024)

## Built on by (most cited first, 16 of 16)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling](https://mlsanity.com/paper/2501.19306/) (2025)
- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling](https://mlsanity.com/paper/2502.17651/) (2025)
- [Optimizing Temperature for Language Models with Multi-Sample Inference](https://mlsanity.com/paper/2502.05234/) (2025)
- [Provable Scaling Laws for the Test-Time Compute of Large Language Models](https://mlsanity.com/paper/2411.19477/) (2024)
- [Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis](https://mlsanity.com/paper/2412.14234/) (2024)
- [ETS: Efficient Tree Search for Inference-Time Scaling](https://mlsanity.com/paper/2502.13575/) (2025)
- [From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning](https://mlsanity.com/paper/2501.11877/) (2025)
- [Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory](https://mlsanity.com/paper/2505.10981/) (2025)
- [AdaBoN: Adaptive Best-of-N Alignment](https://mlsanity.com/paper/2505.12050/) (2025)
- [Latency and Token-Aware Test-Time Compute](https://mlsanity.com/paper/2509.09864/) (2025)
- [DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling](https://mlsanity.com/paper/2506.16043/) (2025)
- [On Calibration of Large Language Models: From Response To Capability](https://mlsanity.com/paper/2602.13540/) (2026)
- [Plan-and-Refine: Diverse and Comprehensive Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.07794/) (2025)

## Abstract (arXiv)

Sampling is a basic operation in many inference-time algorithms of large language models (LLMs). To scale up inference efficiently with a limited compute, it is crucial to find an optimal allocation for sample compute budgets: Which sampling configurations (model, temperature, language, etc.) do we use? How many samples do we generate in each configuration? We formulate these choices as a learning problem and propose OSCA, an algorithm that Optimizes Sample Compute Allocation by finding an optimal mix of different inference configurations. Our experiments show that with our learned mixed allocation, we can achieve accuracy better than the best single configuration with 128x less compute on code generation and 25x less compute on 4 reasoning tasks. OSCA is also shown to be effective in agentic workflows beyond single-turn tasks, achieving a better accuracy on SWE-Bench with 3x less compute than the default configuration. Our code and generations are released at https://github.com/LeiLiLab/OSCA.