# SIMA 2: A Generalist Embodied Agent for Virtual Worlds

arXiv: https://arxiv.org/abs/2512.04797 · HTML: https://mlsanity.com/paper/2512.04797/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 88 of its 123 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 88)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [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)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)

## Built on by (most cited first, 30 of 31)

- [GameDevBench: Evaluating Agentic Capabilities Through Game Development](https://mlsanity.com/paper/2602.11103/) (2026)
- [Graph-based Agent Memory: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2602.05665/) (2026)
- [OpenGame: Open Agentic Coding for Games](https://mlsanity.com/paper/2604.18394/) (2026)
- [SPADE: Self-Play in Adaptive Synthetic Executable Environments](https://mlsanity.com/paper/2608.19197/) (2026)
- [Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing](https://mlsanity.com/paper/2601.04575/) (2026)
- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [Can Vision-Language Models Solve the Shell Game?](https://mlsanity.com/paper/2603.08436/) (2026)
- [GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents](https://mlsanity.com/paper/2603.24329/) (2026)
- [Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning](https://mlsanity.com/paper/2605.00347/) (2026)
- [Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse](https://mlsanity.com/paper/2605.09965/) (2026)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning](https://mlsanity.com/paper/2602.20323/) (2026)
- [Scalable Environments Drive Generalizable Agents](https://mlsanity.com/paper/2605.18181/) (2026)
- [Latent Goal Prediction from Language for Model-Based Planning](https://mlsanity.com/paper/2606.20627/) (2026)
- [Critique of Agent Model](https://mlsanity.com/paper/2606.23991/) (2026)
- [Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science](https://mlsanity.com/paper/2603.28361/) (2026)
- [Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft](https://mlsanity.com/paper/2606.15684/) (2026)
- [SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction](https://mlsanity.com/paper/2608.01652/) (2026)
- [A Vision for Multisensory Intelligence: Sensing, Science, and Synergy](https://mlsanity.com/paper/2601.04563/) (2026)
- [Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning](https://mlsanity.com/paper/2604.20601/) (2026)
- [Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning](https://mlsanity.com/paper/2605.15975/) (2026)
- [VLMs for Videogame Data Annotation](https://mlsanity.com/paper/2608.05949/) (2026)
- [Contrastive World Models](https://mlsanity.com/paper/2609.22175/) (2026)
- [GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay](https://mlsanity.com/paper/2609.25001/) (2026)
- [PUBG Ally: A Conversational Embodied Agent as an AI Teammate](https://mlsanity.com/paper/2609.29837/) (2026)
- [SkillVine: Agent Skill Evolution via Branching Exploration](https://mlsanity.com/paper/2609.32731/) (2026)
- [Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses](https://mlsanity.com/paper/2609.36630/) (2026)
- [Anticipating the Consequences of Curriculum Decisions with Large Language Models](https://mlsanity.com/paper/2610.04604/) (2026)
- [PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence](https://mlsanity.com/paper/2610.07127/) (2026)

## Abstract (arXiv)

We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a significant step toward active, goal-directed interaction within an embodied environment. Unlike prior work (e.g., SIMA 1) limited to simple language commands, SIMA 2 acts as an interactive partner, capable of reasoning about high-level goals, conversing with the user, and handling complex instructions given through language and images. Across a diverse portfolio of games, SIMA 2 substantially closes the gap with human performance and demonstrates robust generalization to previously unseen environments, all while retaining the base model's core reasoning capabilities. Furthermore, we demonstrate a capacity for open-ended self-improvement: by leveraging Gemini to generate tasks and provide rewards, SIMA 2 can autonomously learn new skills from scratch in a new environment. This work validates a path toward creating versatile and continuously learning agents for both virtual and, eventually, physical worlds.