# BeSimulator: A Large Language Model Powered Text-based Behavior Simulator

arXiv: https://arxiv.org/abs/2409.15865 · HTML: https://mlsanity.com/paper/2409.15865/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 52 references that are in the map.
- First posted on arXiv 24 Sep 2024.

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

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving](https://mlsanity.com/paper/2309.17452/) (2023)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Large Language Models as Commonsense Knowledge for Large-Scale Task Planning](https://mlsanity.com/paper/2305.14078/) (2023)
- [REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction](https://mlsanity.com/paper/2306.15724/) (2023)
- [BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation](https://mlsanity.com/paper/2403.09227/) (2024)
- [Chain of Code: Reasoning with a Language Model-Augmented Code Emulator](https://mlsanity.com/paper/2312.04474/) (2023)
- [Behavior Trees in Robotics and AI: An Introduction](https://mlsanity.com/paper/1709.00084/) (2017)
- [Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2406.09136/) (2024)
- [Can Language Models Serve as Text-Based World Simulators?](https://mlsanity.com/paper/2406.06485/) (2024)
- [DKPROMPT: Domain Knowledge Prompting Vision-Language Models for Open-World Planning](https://mlsanity.com/paper/2406.17659/) (2024)
- [Learning Behavior Trees with Genetic Programming in Unpredictable Environments](https://mlsanity.com/paper/2011.03252/) (2020)
- [ARROCH: Augmented Reality for Robots Collaborating with a Human](https://mlsanity.com/paper/2109.10400/) (2021)

## Built on by (most cited first, 1 of 1)

- [PERCEIVE: A Benchmark for Personalized Emotion and Communication Behavior Understanding on Social Media](https://mlsanity.com/paper/2605.12525/) (2026)

## Abstract (arXiv)

Traditional robot simulators focus on physical process modeling and realistic rendering, often suffering from high computational costs, inefficiencies, and limited adaptability. To handle this issue, we concentrate on behavior simulation in robotics to analyze and validate the logic behind robot behaviors, aiming to achieve preliminary evaluation before deploying resource-intensive simulators and thus enhance simulation efficiency. In this paper, we propose BeSimulator, a modular and novel LLM-powered framework, as an attempt towards behavior simulation in the context of text-based environments. By constructing text-based virtual environments and performing semantic-level simulation, BeSimulator can generalize across scenarios and achieve long-horizon complex simulation. Inspired by human cognition paradigm, it employs a ``consider-decide-capture-transfer'' four-phase simulation process, termed Chain of Behavior Simulation (CBS), which excels at analyzing action feasibility and state transition. Additionally, BeSimulator incorporates code-driven reasoning to enable arithmetic operations and enhance reliability, and reflective feedback to refine simulation. Based on our manually constructed behavior-tree-based simulation benchmark, BTSIMBENCH, our experiments show a significant performance improvement in behavior simulation compared to baselines, ranging from 13.60% to 24.80%. Code and data are available at https://github.com/Dawn888888/BeSimulator.