# A Survey of Reinforcement Learning from Human Feedback

arXiv: https://arxiv.org/abs/2312.14925 · HTML: https://mlsanity.com/paper/2312.14925/

## Key facts

- Cited by 264 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 45 of its 424 references that are in the map.
- First posted on arXiv 22 Dec 2023.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

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

- [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)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [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)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [Recursively Summarizing Books with Human Feedback](https://mlsanity.com/paper/2109.10862/) (2021)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)
- [Supervising strong learners by amplifying weak experts](https://mlsanity.com/paper/1810.08575/) (2018)
- [Grounded Language Learning in a Simulated 3D World](https://mlsanity.com/paper/1706.06551/) (2017)
- [Deep Reinforcement Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1902.04257/) (2019)
- [Fine-Tuning Language Models with Advantage-Induced Policy Alignment](https://mlsanity.com/paper/2306.02231/) (2023)
- [The History and Risks of Reinforcement Learning and Human Feedback](https://mlsanity.com/paper/2310.13595/) (2023)
- [Uncertainty Estimation for Language Reward Models](https://mlsanity.com/paper/2203.07472/) (2022)
- [AI Alignment and Social Choice: Fundamental Limitations and Policy Implications](https://mlsanity.com/paper/2310.16048/) (2023)
- [imitation: Clean Imitation Learning Implementations](https://mlsanity.com/paper/2211.11972/) (2022)
- [Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2211.11602/) (2022)

## Built on by (most cited first, 30 of 264)

- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [SecAlign: Defending Against Prompt Injection with Preference Optimization](https://mlsanity.com/paper/2410.05451/) (2024)
- [Agentic Reinforced Policy Optimization](https://mlsanity.com/paper/2507.19849/) (2025)
- [Secrets of RLHF in Large Language Models Part II: Reward Modeling](https://mlsanity.com/paper/2401.06080/) (2024)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [Provably Robust DPO: Aligning Language Models with Noisy Feedback](https://mlsanity.com/paper/2403.00409/) (2024)
- [BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling](https://mlsanity.com/paper/2406.00832/) (2024)
- [What Can RL Bring to VLA Generalization? An Empirical Study](https://mlsanity.com/paper/2505.19789/) (2025)
- [Group Robust Preference Optimization in Reward-free RLHF](https://mlsanity.com/paper/2405.20304/) (2024)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping](https://mlsanity.com/paper/2402.14083/) (2024)
- [RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs](https://mlsanity.com/paper/2404.08555/) (2024)
- [Panacea: Pareto Alignment via Preference Adaptation for LLMs](https://mlsanity.com/paper/2402.02030/) (2024)
- [Tree Search for LLM Agent Reinforcement Learning](https://mlsanity.com/paper/2509.21240/) (2025)
- [On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization](https://mlsanity.com/paper/2405.16455/) (2024)
- [UltraMedical: Building Specialized Generalists in Biomedicine](https://mlsanity.com/paper/2406.03949/) (2024)
- [A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations](https://mlsanity.com/paper/2502.14881/) (2025)
- [Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate](https://mlsanity.com/paper/2509.05396/) (2025)
- [Discrete Diffusion in Large Language and Multimodal Models: A Survey](https://mlsanity.com/paper/2506.13759/) (2025)
- [Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles](https://mlsanity.com/paper/2505.19914/) (2025)
- [A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future](https://mlsanity.com/paper/2504.12328/) (2025)
- [A Survey for Foundation Models in Autonomous Driving](https://mlsanity.com/paper/2402.01105/) (2024)
- [An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents](https://mlsanity.com/paper/2505.15117/) (2025)
- [Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models](https://mlsanity.com/paper/2407.06089/) (2024)
- [Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuning](https://mlsanity.com/paper/2410.05582/) (2024)
- [Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment](https://mlsanity.com/paper/2501.09620/) (2025)
- [Inverse Constitutional AI: Compressing Preferences into Principles](https://mlsanity.com/paper/2406.06560/) (2024)
- [TxGemma: Efficient and Agentic LLMs for Therapeutics](https://mlsanity.com/paper/2504.06196/) (2025)

## Abstract (arXiv)

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of preference-based reinforcement learning (PbRL), it stands at the intersection of artificial intelligence and human-computer interaction. This positioning provides a promising approach to enhance the performance and adaptability of intelligent systems while also improving the alignment of their objectives with human values. The success in training large language models (LLMs) has impressively demonstrated this potential in recent years, where RLHF has played a decisive role in directing the model's capabilities towards human objectives. This article provides an overview of the fundamentals of RLHF, exploring how RL agents interact with human feedback. While recent focus has been on RLHF for LLMs, our survey covers the technique across multiple domains. We provide our most comprehensive coverage in control and robotics, where many fundamental techniques originate, alongside a dedicated LLM section. We examine the core principles that underpin RLHF, how algorithms and human feedback work together, and the main research trends in the field. Our goal is to give researchers and practitioners a clear understanding of this rapidly growing field.