# Self-Evolved Reward Learning for LLMs

arXiv: https://arxiv.org/abs/2411.00418 · HTML: https://mlsanity.com/paper/2411.00418/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 1 Nov 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)
- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)

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

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [UltraFeedback: Boosting Language Models with Scaled AI Feedback](https://mlsanity.com/paper/2310.01377/) (2023)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://mlsanity.com/paper/2312.06585/) (2023)
- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [AutoML-GPT: Automatic Machine Learning with GPT](https://mlsanity.com/paper/2305.02499/) (2023)
- [Language Model Self-improvement by Reinforcement Learning Contemplation](https://mlsanity.com/paper/2305.14483/) (2023)

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

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Text2Grad: Reinforcement Learning from Natural Language Feedback](https://mlsanity.com/paper/2505.22338/) (2025)
- [IPO: Your Language Model is Secretly a Preference Classifier](https://mlsanity.com/paper/2502.16182/) (2025)
- [CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards](https://mlsanity.com/paper/2512.23971/) (2025)
- [A Survey on Efficient Large Language Model Training: From Data-centric Perspectives](https://mlsanity.com/paper/2510.25817/) (2025)
- [RLTHF: Targeted Human Feedback for LLM Alignment](https://mlsanity.com/paper/2502.13417/) (2025)
- [Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey](https://mlsanity.com/paper/2510.01925/) (2025)
- [Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution](https://mlsanity.com/paper/2503.01695/) (2025)
- [Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2505.21907/) (2025)
- [Self-Improving Model Steering](https://mlsanity.com/paper/2507.08967/) (2025)
- [Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning](https://mlsanity.com/paper/2510.17923/) (2025)
- [Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis](https://mlsanity.com/paper/2509.26074/) (2025)
- [Towards AGI A Pragmatic Approach Towards Self Evolving Agent](https://mlsanity.com/paper/2601.11658/) (2026)
- [Self-evolving Embodied AI](https://mlsanity.com/paper/2602.04411/) (2026)
- [Cleansing the Artificial Mind: A Self-Reflective Detoxification Framework for Large Language Models](https://mlsanity.com/paper/2601.11776/) (2026)
- [How Can Recommendation Feedback Evolve Agent Memory?](https://mlsanity.com/paper/2609.37544/) (2026)

## Abstract (arXiv)

Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversational models like GPT-4, ChatGPT, and Llama 2. A core challenge in employing RLHF lies in training a reliable reward model (RM), which relies on high-quality labels typically provided by human experts or advanced AI system. These methods can be costly and may introduce biases that affect the language model's responses. As language models improve, human input may become less effective in further enhancing their performance. In this paper, we propose Self-Evolved Reward Learning (SER), a novel approach where the RM generates additional training data to iteratively improve itself. We conducted extensive experiments on multiple datasets such as HH-RLHF and UltraFeedback, using models like Mistral and Llama 3, and compare SER against various baselines. Our results demonstrate that even with limited human-annotated data, learning from self-feedback can robustly enhance RM performance, thereby boosting the capabilities of large language models (LLMs). Resources of this paper can be found at https://aka.ms/ser