mlsanityData to 14 Oct 2026

Generative Embodied Multiple Behavior Control Systems for Human-like Agents

arXiv 2609.22691 ↗First posted 19 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Building human-like agents that reproduce human behavior in realistic 3D environments has been a longstanding objective in AI. Existing human-like agent frameworks primarily focus on modeling goal-directed behavior. However, cognitive neuroscience commonly believes that human behaviors are more likely controlled by multiple control systems, including goal-directed and habitual behavior control systems. Habitual behavior has been largely overlooked though it plays a crucial role in human daily life. In this paper, we address this gap by proposing a multiple control systems setup that jointly models goal-directed and habitual behaviors. Building on this setup, we propose GEMS, in which the Habitual Controller retrieves habitual actions from habit memory in response to relevant environmental stimuli, while the Goal-directed Controller proposes goal-directed actions and estimates their values. The Arbiter dynamically governs the relative influence of each controller and selects the final action. To construct diverse human-level behavior instructions in 3D environments, we further develop a keyframe-guided motion generation module. Extensive quantitative evaluations, human and ablation studies demonstrate that human-likeness performance is substantially improved by GEMS. The efficacy of GEMS indicates the benefits of leveraging habitual behavior and multiple behavior control system coordination for believable embodied human-like agents. The code is available at hrefhttps://anonymous.4open.science/r/review-video-82f4/demo.mp4this link.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 72 references that are in the map. First posted on arXiv 19 Sep 2026.

Builds on

30 of 72 references.

References · 30

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2023Cognitive Architectures for Language Agentscited by 429
  3. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 238
  4. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
  5. 2022HUMANISE: Language-conditioned Human Motion Generation in 3D Scenescited by 158
  6. 2024Scaling Up Dynamic Human-Scene Interaction Modelingcited by 137
  7. 2023Synthesizing Physical Character-Scene Interactionscited by 104
  8. 2025EgoLife: Towards Egocentric Life Assistantcited by 91
  9. 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modellingcited by 88
  10. 2023Humanoid Agents: Platform for Simulating Human-like Generative Agentscited by 73
  11. 2024Human-Object Interaction from Human-Level Instructionscited by 64
  12. 2024Diffusion Self-Distillation for Zero-Shot Customized Image Generationcited by 47
18 more
  1. 2023Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learningcited by 45
  2. 2026Kimodo: Scaling Controllable Human Motion Generationcited by 37
  3. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  4. 2024Simulating Human-like Daily Activities with Desire-driven Autonomycited by 30
  5. 2024WANDR: Intention-guided Human Motion Generationcited by 26
  6. 2026Reinforcement World Model Learning for LLM-based Agentscited by 24
  7. 2025Virtual Community: An Open World for Humans, Robots, and Societycited by 13
  8. 2024Affordable Generative Agentscited by 9
  9. 2024AFSPP: Agent Framework for Shaping Preference and Personality with Large Language Modelscited by 7
  10. 2026Bridging the Agent-World Gap: Text World Models for LLM-based Agentscited by 5
  11. 2025AgentSense: Virtual Sensor Data Generation Using LLM Agents in Simulated Home Environmentscited by 4
  12. 2025Ella: Embodied Social Agents with Lifelong Memorycited by 4
  13. 2026InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinementcited by 3
  14. 2025TSTMotion: Training-free Scene-aware Text-to-motion Generationcited by 2
  15. 2026Beyond Self-Interest: Modeling Social-Oriented Motivation for Human-like Multi-Agent Interactionscited by 2
  16. 2026Context-Value-Action Architecture for Value-Driven Large Language Model Agentscited by 2
  17. 2026Visually-grounded Humanoid Agentscited by 2
  18. 2024HabitAction: A Video Dataset for Human Habitual Behavior Recognitioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026World Models for Embodied Intelligence: From Plausible to Controllable to Actionable
  2. 2026Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models
  3. 2026Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
  4. 2026Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
  5. 2022Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback
  6. 2026RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy
  7. 2025Communication-Efficient Desire Alignment for Embodied Agent-Human Adaptation
  8. 2024Dynamic planning in hierarchical active inference