# Large Language Models as Generalizable Policies for Embodied Tasks

arXiv: https://arxiv.org/abs/2310.17722 · HTML: https://mlsanity.com/paper/2310.17722/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- Builds on 75 of its 108 references that are in the map.
- First posted on arXiv 26 Oct 2023.

## Builds on (most cited first, 30 of 75)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (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)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)

## Built on by (most cited first, 30 of 86)

- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning](https://mlsanity.com/paper/2405.10292/) (2024)
- [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://mlsanity.com/paper/2503.15478/) (2025)
- [Improving Vision-Language-Action Model with Online Reinforcement Learning](https://mlsanity.com/paper/2501.16664/) (2025)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [Vision Language Models are In-Context Value Learners](https://mlsanity.com/paper/2411.04549/) (2024)
- [DrEureka: Language Model Guided Sim-To-Real Transfer](https://mlsanity.com/paper/2406.01967/) (2024)
- [EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents](https://mlsanity.com/paper/2501.11858/) (2025)
- [QUAR-VLA: Vision-Language-Action Model for Quadruped Robots](https://mlsanity.com/paper/2312.14457/) (2023)
- [ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos](https://mlsanity.com/paper/2406.19392/) (2024)
- [Matryoshka Query Transformer for Large Vision-Language Models](https://mlsanity.com/paper/2405.19315/) (2024)
- [From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons](https://mlsanity.com/paper/2412.08442/) (2024)
- [Agents Thinking Fast and Slow: A Talker-Reasoner Architecture](https://mlsanity.com/paper/2410.08328/) (2024)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [Grounding Multimodal Large Language Models in Actions](https://mlsanity.com/paper/2406.07904/) (2024)
- [GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robot](https://mlsanity.com/paper/2403.13358/) (2024)
- [Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective](https://mlsanity.com/paper/2510.15047/) (2025)
- [World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning](https://mlsanity.com/paper/2503.10480/) (2025)
- [3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model](https://mlsanity.com/paper/2505.22657/) (2025)
- [FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading](https://mlsanity.com/paper/2502.11433/) (2025)
- [Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning](https://mlsanity.com/paper/2504.00907/) (2025)
- [RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedback](https://mlsanity.com/paper/2505.19767/) (2025)
- [Holistic Evaluation of GPT-4V for Biomedical Imaging](https://mlsanity.com/paper/2312.05256/) (2023)
- [Eurekaverse: Environment Curriculum Generation via Large Language Models](https://mlsanity.com/paper/2411.01775/) (2024)
- [NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains](https://mlsanity.com/paper/2503.00870/) (2025)
- [Reflect-RL: Two-Player Online RL Fine-Tuning for LMs](https://mlsanity.com/paper/2402.12621/) (2024)
- [Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration](https://mlsanity.com/paper/2601.10744/) (2026)
- [Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy](https://mlsanity.com/paper/2503.10049/) (2025)
- [FindingDory: A Benchmark to Evaluate Memory in Embodied Agents](https://mlsanity.com/paper/2506.15635/) (2025)
- [Multi-Modal Grounded Planning and Efficient Replanning For Learning Embodied Agents with A Few Examples](https://mlsanity.com/paper/2412.17288/) (2024)

## Abstract (arXiv)

We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as input text instructions and visual egocentric observations and output actions directly in the environment. Using reinforcement learning, we train LLaRP to see and act solely through environmental interactions. We show that LLaRP is robust to complex paraphrasings of task instructions and can generalize to new tasks that require novel optimal behavior. In particular, on 1,000 unseen tasks it achieves 42% success rate, 1.7x the success rate of other common learned baselines or zero-shot applications of LLMs. Finally, to aid the community in studying language conditioned, massively multi-task, embodied AI problems we release a novel benchmark, Language Rearrangement, consisting of 150,000 training and 1,000 testing tasks for language-conditioned rearrangement. Video examples of LLaRP in unseen Language Rearrangement instructions are at https://llm-rl.github.io.