Classical GNNs push messages with one global rule per layer—great for tidy graphs, brittle for messy ones. ReaGAN (Retrieval-augmented Graph Agentic Network) breaks that mold by treating each node as an autonomous agent that decides whether to aggregate locally, retrieve globally, predict now, or do nothing—based on its own memory and a plan drafted by a frozen LLM.
What’s new
-
Node-level autonomy. At every layer, a node queries the LLM for an action plan, executes it, and updates memory—no globally synchronized rulebook.
-
Local + global context. Beyond neighbors in the graph, nodes invoke RAG to retrieve semantically similar but structurally distant nodes, then fuse both sources.
-
Memory as glue. Nodes persist aggregated text snippets and few-shot (text, label) exemplars, enabling in-context prediction later.
Why it matters
Real-world graphs are sparse and noisy; uniform propagation amplifies junk. ReaGAN’s per-node planning and local-global retrieval adapt to informativeness imbalances and long-range semantics—key gaps in standard GNNs. In experiments, the authors report competitive few-shot performance using only a frozen LLM (no fine-tuning), highlighting a compute-friendly path for graph ML.
How it runs (at a glance)
Each node iterates a loop: perceive → plan → act (LocalAggregation / GlobalAggregation / Predict / NoOp) → update memory. A simple algorithmic skeleton formalizes the layer-wise cycle and action space.
Paper link: https://arxiv.org/pdf/2508.00429
