mlsanityData to 7 Oct 2026

Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents

arXiv 2604.27699 ↗First posted 30 Apr 2026cs.AIcited by 0

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Current embodied agents are often limited to passive instruction-following or reactive need-satisfaction, lacking a stable, high-order value framework essential for long-term, self-directed behavior and resolving motivational conflicts. We introduce textitValuePlanner, a hierarchical cognitive architecture that decouples high-level value scheduling from low-level action execution. textitValuePlanner employs an LLM-based cognitive module to generate symbolic subgoals by reasoning through abstract value trade-offs, which are then translated into executable action plans by a classical PDDL planner. This process is refined via a closed-loop feedback mechanism. Evaluating such autonomy requires methods beyond task-success rates, and we therefore propose a value-centric evaluation suite measuring cumulative value gain, preference alignment, and behavioral diversity. Experiments in the TongSim household environment demonstrate that textitValuePlanner arbitrates competing values to generate coherent, long-horizon, self-directed behavior absent from instruction-following and needs-driven baselines. Our work offers a structured approach to bridging intrinsic values and grounded behavior for autonomous agents.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 37 of its 62 references that are in the map. First posted on arXiv 30 Apr 2026.

Builds on

37 of 62 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Agentic Robot: A Brain-Inspired Framework for Vision-Language-Action Models in Embodied Agents29 May
  2. 2024Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making9 Oct
  3. 2023An Embodied Generalist Agent in 3D World18 Nov
  4. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models8 Dec

Other references · 33

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  5. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  6. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  7. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  8. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  9. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 178
  10. 2023REFLECT: Summarizing Robot Experiences for Failure Explanation and Correctioncited by 171
  11. 2024Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustmentcited by 171
  12. 2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 132
21 more
  1. 2014The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarkscited by 86
  2. 20243D-Mem: 3D Scene Memory for Embodied Exploration and Reasoningcited by 73
  3. 2023MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perceptioncited by 67
  4. 2023Dynamic Planning with a LLMcited by 60
  5. 2022How Different Groups Prioritize Ethical Values for Responsible AIcited by 49
  6. 2022Plansformer: Generating Symbolic Plans using Transformerscited by 41
  7. 2025PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PCcited by 39
  8. 2021ValueNet: A New Dataset for Human Value Driven Dialogue Systemcited by 34
  9. 2024Simulating Human-like Daily Activities with Desire-driven Autonomycited by 30
  10. 2024TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Modelscited by 29
  11. 2024UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AIcited by 25
  12. 2024ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Modelscited by 19
  13. 2024On the Limit of Language Models as Planning Formalizerscited by 17
  14. 2024Can LLM be a Good Path Planner based on Prompt Engineering? Mitigating the Hallucination for Path Planningcited by 11
  15. 2024Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspectivecited by 9
  16. 2025Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verificationcited by 9
  17. 2024Language-Augmented Symbolic Planner for Open-World Task Planningcited by 8
  18. 2024UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activitycited by 4
  19. 2025Deliberate Planning in Language Models with Symbolic Representationcited by 3
  20. 2025Active Semantic Perceptioncited by 3
  21. 2023Heuristic Satisficing Inferential Decision Making in Human and Robot Active Perceptioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
  2. 2026Context-Value-Action Architecture for Value-Driven Large Language Model Agents
  3. 2026From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based Agents
  4. 2024Value Internalization: Learning and Generalizing from Social Reward
  5. 2026Beyond Self-Interest: Modeling Social-Oriented Motivation for Human-like Multi-Agent Interactions
  6. 2026RobotValues: Evaluating Household Robots When Human Values Conflict
  7. 2023Physical Reasoning and Object Planning for Household Embodied Agents
  8. 2024Democratizing Reward Design for Personal and Representative Value-Alignment