# LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence

arXiv: https://arxiv.org/abs/2405.17424 · HTML: https://mlsanity.com/paper/2405.17424/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 27 May 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [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)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments](https://mlsanity.com/paper/1811.12354/) (2018)
- [MineRL: A Large-Scale Dataset of Minecraft Demonstrations](https://mlsanity.com/paper/1907.13440/) (2019)
- [See and Think: Embodied Agent in Virtual Environment](https://mlsanity.com/paper/2311.15209/) (2023)
- [Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks](https://mlsanity.com/paper/2303.16563/) (2023)
- [LLaMA Rider: Spurring Large Language Models to Explore the Open World](https://mlsanity.com/paper/2310.08922/) (2023)
- [Embodied Evolution in Collective Robotics: A Review](https://mlsanity.com/paper/1709.08992/) (2017)
- [Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft](https://mlsanity.com/paper/2003.06066/) (2020)
- [Improving Deep Reinforcement Learning in Minecraft with Action Advice](https://mlsanity.com/paper/1908.01007/) (2019)

## Built on by (most cited first, 10 of 10)

- [Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle](https://mlsanity.com/paper/2509.16679/) (2025)
- [The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break](https://mlsanity.com/paper/2604.11978/) (2026)
- [Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs](https://mlsanity.com/paper/2512.03324/) (2025)
- [Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization](https://mlsanity.com/paper/2506.10357/) (2025)
- [VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft](https://mlsanity.com/paper/2508.18722/) (2025)
- [Training Transformers for KV Cache Compressibility](https://mlsanity.com/paper/2605.05971/) (2026)
- [Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraft](https://mlsanity.com/paper/2503.03505/) (2025)
- [SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding](https://mlsanity.com/paper/2603.09036/) (2026)
- [How Social is It? A Benchmark for LLMs' Capabilities in Multi-user Multi-turn Social Agent Tasks](https://mlsanity.com/paper/2505.04628/) (2025)
- [WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning](https://mlsanity.com/paper/2606.12852/) (2026)

## Abstract (arXiv)

Recent embodied agents are primarily built based on reinforcement learning (RL) or large language models (LLMs). Among them, RL agents are efficient for deployment but only perform very few tasks. By contrast, giant LLM agents (often more than 1000B parameters) present strong generalization while demanding enormous computing resources. In this work, we combine their advantages while avoiding the drawbacks by conducting the proposed referee RL on our developed large auto-regressive model (LARM). Specifically, LARM is built upon a lightweight LLM (fewer than 5B parameters) and directly outputs the next action to execute rather than text. We mathematically reveal that classic RL feedbacks vanish in long-horizon embodied exploration and introduce a giant LLM based referee to handle this reward vanishment during training LARM. In this way, LARM learns to complete diverse open-world tasks without human intervention. Especially, LARM successfully harvests enchanted diamond equipment in Minecraft, which demands significantly longer decision-making chains than the highest achievements of prior best methods.