# Dynamic Scaling of Unit Tests for Code Reward Modeling

arXiv: https://arxiv.org/abs/2501.01054 · HTML: https://mlsanity.com/paper/2501.01054/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 13 of its 44 references that are in the map.
- First posted on arXiv 2 Jan 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [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)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [TACO: Topics in Algorithmic COde generation dataset](https://mlsanity.com/paper/2312.14852/) (2023)
- [Learning How Hard to Think: Input-Adaptive Allocation of LM Computation](https://mlsanity.com/paper/2410.04707/) (2024)
- [Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling](https://mlsanity.com/paper/2408.16737/) (2024)

## Built on by (most cited first, 30 of 33)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning](https://mlsanity.com/paper/2504.12216/) (2025)
- [Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning](https://mlsanity.com/paper/2506.03136/) (2025)
- [MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation](https://mlsanity.com/paper/2502.12468/) (2025)
- [AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery](https://mlsanity.com/paper/2604.05550/) (2026)
- [SWE-Universe: Scale Real-World Verifiable Environments to Millions](https://mlsanity.com/paper/2602.02361/) (2026)
- [A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2510.01132/) (2025)
- [Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning](https://mlsanity.com/paper/2510.23038/) (2025)
- [Rethinking Verification for LLM Code Generation: From Generation to Testing](https://mlsanity.com/paper/2507.06920/) (2025)
- [Learning to Generate Unit Test via Adversarial Reinforcement Learning](https://mlsanity.com/paper/2508.21107/) (2025)
- [Teaching Your Models to Understand Code via Focal Preference Alignment](https://mlsanity.com/paper/2503.02783/) (2025)
- [Scoring Verifiers: Evaluating Synthetic Verification for Code and Reasoning](https://mlsanity.com/paper/2502.13820/) (2025)
- [Scaling Coding Agents via Atomic Skills](https://mlsanity.com/paper/2604.05013/) (2026)
- [Scaling Agentic Verifier for Competitive Coding](https://mlsanity.com/paper/2602.04254/) (2026)
- [MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms](https://mlsanity.com/paper/2502.06556/) (2025)
- [When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems](https://mlsanity.com/paper/2605.12947/) (2026)
- [Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation](https://mlsanity.com/paper/2605.15669/) (2026)
- [Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification](https://mlsanity.com/paper/2605.17609/) (2026)
- [CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning](https://mlsanity.com/paper/2601.22803/) (2026)
- [MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning](https://mlsanity.com/paper/2603.01409/) (2026)
- [Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus](https://mlsanity.com/paper/2603.29292/) (2026)
- [Granularity-Regulated Adaptive Computational Efficiency for Optimal Verification in Test-Time Scaling](https://mlsanity.com/paper/2606.19354/) (2026)
- [VeriBound: PAC-Bayesian Generalization Bounds for Process Reward Models Trained with Formal Verification Tools](https://mlsanity.com/paper/2606.20740/) (2026)
- [The geometry of AI validation: From structural blindness to reusable audits](https://mlsanity.com/paper/2608.21496/) (2026)
- [Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs](https://mlsanity.com/paper/2609.03955/) (2026)
- [Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-Debugging](https://mlsanity.com/paper/2602.03181/) (2026)
- [Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization](https://mlsanity.com/paper/2605.13229/) (2026)
- [The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms](https://mlsanity.com/paper/2606.25450/) (2026)
- [Function-Level Execution Feedback for Code Preference Optimization](https://mlsanity.com/paper/2608.23632/) (2026)
- [Robust Code RL via Faulty-Code-Driven Test case Synthesis and Dense Reward Shaping](https://mlsanity.com/paper/2608.24135/) (2026)

## Abstract (arXiv)

Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we explore the impact of scaling unit tests to enhance reward signal quality. Our pioneer experiment reveals a positive correlation between the number of unit tests and reward signal quality, with greater benefits observed in more challenging problems. Based on these insights, we propose CodeRM-8B, a lightweight yet effective unit test generator that enables efficient and high-quality unit test scaling. Additionally, we implement a dynamic scaling mechanism that adapts the number of unit tests based on problem difficulty, further improving efficiency. Experimental results show that our approach significantly improves performance across various models on three benchmarks (e.g., with gains of 18.43% for Llama3-8B and 3.42% for GPT-4o-mini on HumanEval Plus).