# Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena

arXiv: https://arxiv.org/abs/2407.10627 · HTML: https://mlsanity.com/paper/2407.10627/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 81 of its 101 references that are in the map.
- First posted on arXiv 15 Jul 2024.

## Builds on (most cited first, 30 of 81)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)

## Built on by (most cited first, 26 of 26)

- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [Self-Boosting Large Language Models with Synthetic Preference Data](https://mlsanity.com/paper/2410.06961/) (2024)
- [AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent](https://mlsanity.com/paper/2512.20745/) (2025)
- [Training Language Models to Critique With Multi-agent Feedback](https://mlsanity.com/paper/2410.15287/) (2024)
- [Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support](https://mlsanity.com/paper/2510.06674/) (2025)
- [LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient](https://mlsanity.com/paper/2502.01683/) (2025)
- [ScIRGen: Synthesize Realistic and Large-Scale RAG Dataset for Scientific Research](https://mlsanity.com/paper/2506.11117/) (2025)
- [Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents](https://mlsanity.com/paper/2601.18217/) (2026)
- [Benchmark Everything Everywhere All at Once](https://mlsanity.com/paper/2606.06462/) (2026)
- [Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management](https://mlsanity.com/paper/2505.03756/) (2025)
- [CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback](https://mlsanity.com/paper/2507.22080/) (2025)
- [BALSAM: A Platform for Benchmarking Arabic Large Language Models](https://mlsanity.com/paper/2507.22603/) (2025)
- [DrugAgent: Reliable Multi-Agent Integration of Conflicting Biomedical Evidence for Drug-Target Interaction Assessment](https://mlsanity.com/paper/2408.13378/) (2024)
- [DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation](https://mlsanity.com/paper/2511.06307/) (2025)
- [STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability](https://mlsanity.com/paper/2606.19236/) (2026)
- [From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap](https://mlsanity.com/paper/2410.20791/) (2024)
- [Project MPG: towards a generalized performance benchmark for LLM capabilities](https://mlsanity.com/paper/2410.22368/) (2024)
- [SHERLOCK: Towards Dynamic Knowledge Adaptation in LLM-enhanced E-commerce Risk Management](https://mlsanity.com/paper/2510.08948/) (2025)
- [Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis](https://mlsanity.com/paper/2603.12997/) (2026)
- [Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence](https://mlsanity.com/paper/2605.06230/) (2026)
- [WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models](https://mlsanity.com/paper/2412.17395/) (2024)
- [The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)](https://mlsanity.com/paper/2505.10640/) (2025)
- [Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent Improvement](https://mlsanity.com/paper/2510.27051/) (2025)
- [Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models](https://mlsanity.com/paper/2605.28828/) (2026)
- [Multi-LLM Collaborative Alignment via Stackelberg Games](https://mlsanity.com/paper/2609.39076/) (2026)

## Abstract (arXiv)

Assessing the effectiveness of large language models (LLMs) presents substantial challenges. The method of conducting human-annotated battles in an online Chatbot Arena is a highly effective evaluative technique. However, this approach is limited by the costs and time required for human annotation. In this paper, we introduce Arena Learning, an innovative offline strategy designed to simulate these arena battles using AI-driven annotations to evaluate battle outcomes, thus facilitating the continuous improvement of the target model through both supervised fine-tuning and reinforcement learning. Arena Learning comprises two key elements. First, it ensures precise evaluations and maintains consistency between offline simulations and online competitions via WizardArena, a pipeline developed to accurately predict the Elo rankings of various models using a meticulously designed offline test set. Our results demonstrate that WizardArena's predictions closely align with those from the online Arena. Second, it involves the continuous improvement of training data based on the battle results and the refined model. We establish a data flywheel to iteratively update the training data by highlighting the weaknesses of the target model based on its battle results, enabling it to learn from the strengths of multiple different models. We apply Arena Learning to train our target model, WizardLM-β, and demonstrate significant performance enhancements across various metrics. This fully automated training and evaluation pipeline sets the stage for continuous advancements in various LLMs via post-training. Notably, Arena Learning plays a pivotal role in the success of WizardLM-2, and this paper serves both as an exploration of its efficacy and a foundational study for future discussions related to WizardLM-2 and its derivatives.