# LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning

arXiv: https://arxiv.org/abs/2502.05453 · HTML: https://mlsanity.com/paper/2502.05453/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 80 references that are in the map.
- First posted on arXiv 8 Feb 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 31)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Emergent Multi-Agent Communication in the Deep Learning Era](https://mlsanity.com/paper/2006.02419/) (2020)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction](https://mlsanity.com/paper/1809.00786/) (2018)
- [Skill Induction and Planning with Latent Language](https://mlsanity.com/paper/2110.01517/) (2021)
- [Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning](https://mlsanity.com/paper/2402.16801/) (2024)
- [Learning Nearly Decomposable Value Functions Via Communication Minimization](https://mlsanity.com/paper/1910.05366/) (2019)
- [Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks](https://mlsanity.com/paper/2408.03615/) (2024)
- [Distilling Script Knowledge from Large Language Models for Constrained Language Planning](https://mlsanity.com/paper/2305.05252/) (2023)
- [Plansformer: Generating Symbolic Plans using Transformers](https://mlsanity.com/paper/2212.08681/) (2022)
- [BenchMARL: Benchmarking Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2312.01472/) (2023)
- [Multi-agent Reinforcement Learning: A Comprehensive Survey](https://mlsanity.com/paper/2312.10256/) (2023)
- [PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration](https://mlsanity.com/paper/2203.08553/) (2022)
- [HoME: a Household Multimodal Environment](https://mlsanity.com/paper/1711.11017/) (2017)
- [An LLM-Based Digital Twin for Optimizing Human-in-the Loop Systems](https://mlsanity.com/paper/2403.16809/) (2024)
- [Real-time Network Intrusion Detection via Decision Transformers](https://mlsanity.com/paper/2312.07696/) (2023)

## Built on by (most cited first, 18 of 18)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate](https://mlsanity.com/paper/2509.05396/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [Graph-based Agent Memory: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2602.05665/) (2026)
- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2605.07358/) (2026)
- [Toward Efficient Agents: Memory, Tool learning, and Planning](https://mlsanity.com/paper/2601.14192/) (2026)
- [Neural Brain: A Neuroscience-inspired Framework for Embodied Agents](https://mlsanity.com/paper/2505.07634/) (2025)
- [The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs](https://mlsanity.com/paper/2602.11583/) (2026)
- [AI Agent Behavioral Science](https://mlsanity.com/paper/2506.06366/) (2025)
- [DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration](https://mlsanity.com/paper/2511.04646/) (2025)
- [AURA: Adaptive Unified Reasoning and Automation with LLM-Guided MARL for NextG Cellular Networks](https://mlsanity.com/paper/2511.17506/) (2025)
- [Benchmarking Open-Ended Multi-Agent Coordination in Language Agents](https://mlsanity.com/paper/2606.08340/) (2026)
- [DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths](https://mlsanity.com/paper/2603.00309/) (2026)
- [COOP2: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems](https://mlsanity.com/paper/2603.00349/) (2026)
- [FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs](https://mlsanity.com/paper/2608.18736/) (2026)
- [MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks](https://mlsanity.com/paper/2609.29015/) (2026)
- [Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing](https://mlsanity.com/paper/2610.12711/) (2026)

## Abstract (arXiv)

Developing intelligent agents for long-term cooperation in dynamic open-world scenarios is a major challenge in multi-agent systems. Traditional Multi-agent Reinforcement Learning (MARL) frameworks like centralized training decentralized execution (CTDE) struggle with scalability and flexibility. They require centralized long-term planning, which is difficult without custom reward functions, and face challenges in processing multi-modal data. CTDE approaches also assume fixed cooperation strategies, making them impractical in dynamic environments where agents need to adapt and plan independently. To address decentralized multi-agent cooperation, we propose Decentralized Adaptive Knowledge Graph Memory and Structured Communication System (DAMCS) in a novel Multi-agent Crafter environment. Our generative agents, powered by Large Language Models (LLMs), are more scalable than traditional MARL agents by leveraging external knowledge and language for long-term planning and reasoning. Instead of fully sharing information from all past experiences, DAMCS introduces a multi-modal memory system organized as a hierarchical knowledge graph and a structured communication protocol to optimize agent cooperation. This allows agents to reason from past interactions and share relevant information efficiently. Experiments on novel multi-agent open-world tasks show that DAMCS outperforms both MARL and LLM baselines in task efficiency and collaboration. Compared to single-agent scenarios, the two-agent scenario achieves the same goal with 63% fewer steps, and the six-agent scenario with 74% fewer steps, highlighting the importance of adaptive memory and structured communication in achieving long-term goals. We publicly release our project at: https://happyeureka.github.io/damcs.