# Node-as-Agent: Graph Agentic Network

arXiv: https://arxiv.org/abs/2508.00429 · HTML: https://mlsanity.com/paper/2508.00429/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 1 Aug 2025.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 17 of 17)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Adaptive Universal Generalized PageRank Graph Neural Network](https://mlsanity.com/paper/2006.07988/) (2020)
- [MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing](https://mlsanity.com/paper/1905.00067/) (2019)
- [Visual Agents as Fast and Slow Thinkers](https://mlsanity.com/paper/2408.08862/) (2024)
- [Knowledge Graph Large Language Model (KG-LLM) for Link Prediction](https://mlsanity.com/paper/2403.07311/) (2024)
- [OmniRouter: Budget and Performance Controllable Multi-LLM Routing](https://mlsanity.com/paper/2502.20576/) (2025)
- [LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models](https://mlsanity.com/paper/2503.03313/) (2025)
- [DynLLM: When Large Language Models Meet Dynamic Graph Recommendation](https://mlsanity.com/paper/2405.07580/) (2024)
- [Are Large Language Models In-Context Graph Learners?](https://mlsanity.com/paper/2502.13562/) (2025)
- [Prompt-Based Spatio-Temporal Graph Transfer Learning](https://mlsanity.com/paper/2405.12452/) (2024)
- [Know the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System Design](https://mlsanity.com/paper/2505.16979/) (2025)
- [Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience](https://mlsanity.com/paper/2306.06909/) (2023)

## Built on by (most cited first, 2 of 2)

- [Cache Mechanism for Agent RAG Systems](https://mlsanity.com/paper/2511.02919/) (2025)
- [Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration](https://mlsanity.com/paper/2605.08077/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved remarkable success in graph-based learning by propagating information among neighbor nodes via predefined aggregation mechanisms. However, such fixed schemes often suffer from two key limitations. First, they cannot handle the imbalance in node informativeness -- some nodes are rich in information, while others remain sparse. Second, predefined message passing primarily leverages local structural similarity while ignoring global semantic relationships across the graph, limiting the model's ability to capture distant but relevant information. We propose Retrieval-augmented Graph Agentic Network (ReaGAN), an agent-based framework that empowers each node with autonomous, node-level decision-making. Each node acts as an agent that independently plans its next action based on its internal memory, enabling node-level planning and adaptive message propagation. Additionally, retrieval-augmented generation (RAG) allows nodes to access semantically relevant content and build global relationships in the graph. ReaGAN achieves competitive performance under few-shot in-context settings using a frozen LLM backbone without fine-tuning, showcasing the potential of agentic planning and local-global retrieval in graph learning.