6 papers

Knowledge Graphs

Graph-structured memory and retrieval for agents that need to connect facts.

Papers
6
Read time
1.7h
Avg length
17m
01
Knowledge Graphs

Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects

When your LLM agents start hallucinating plans, forgetting context, fumbling tools, and stepping on each other, the fix is almost always the same primitive you already half-use — a graph — and this survey is the field map for where to put it.

YIXIN LIU, GUIBIN ZHANG, KUN WANG, SHIYUAN LI, SHIRUI PAN · 2025
Read
16 min
Source
arXiv:2507.21407
02
Knowledge Graphs

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

Instead of retrieving a graph once and hoping the LLM can reason over it, Graph-R1 turns retrieval into a multi-turn "think → query → read → rethink → answer" agent loop and trains that whole loop end-to-end with reinforcement learning, so a small 7B model beats GPT-4o-mini GraphRAG pipelines on multi-hop QA.

HAORAN LUO, HAIHONG E, ET AL. (BUPT / NTU / NUS) · JUL 2025
Read
18 min
Source
arXiv:2507.21892
03
Knowledge Graphs

GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models

GRIL trains a graph retriever and an LLM *together* so the retriever learns to fetch the exact facts the LLM actually needs to answer a question, instead of guessing what looks relevant and hoping it helps.

JIALIN CHEN, HOUYU ZHANG, SEONGJUN YUN, ALEJANDRO MOTTINI, REX YING, XIANG SONG, VASSILIS N. IOANNIDIS, ZHENG LI, QINGJUN CUI (YALE · AMAZON)
Read
18 min
Source
arXiv:2509.16502
04
Knowledge Graphs

Knowledge Graph Engineering for Multi-Agentic Systems: The Anthropic Playbook

Replace the entire trained-model NLP pipeline (NER + relation classifier + resolution heuristics) with four Claude prompts that turn a pile of documents into a queryable, provenance-carrying knowledge graph — and use that graph as the shared memory, fact-checker, and persistent world model your multi-agent systems have been missing.

INDEPENDENT SYNTHESIS · JULY 2026 · BASED ON ANTHROPIC'S KNOWLEDGE GRAPH COOKBOOK + "BUILDING EFFECTIVE AI AGENTS"
Read
20 min
05
Knowledge Graphs

RAG vs. GraphRAG: A Systematic Evaluation and Key Insights

A head-to-head benchmark proving RAG and GraphRAG aren't rivals but complements — plain RAG wins on detailed/single-hop questions, GraphRAG wins on multi-hop reasoning and diverse summaries — so the real win is a router or a merge, not picking one.

HAN, WANG, SHOMER, LEI, GUO, HUA, LONG, LIU, TANG (MICHIGAN STATE · OREGON · META)
Read
16 min
Source
arXiv:2502.11371
06
Knowledge Graphs

ReaGAN: Node-as-Agent-Reasoning Graph Agentic Network

Turn every node in a graph into its own little LLM agent that decides — per node, per layer — whether to gather info from its graph neighbors, retrieve semantically similar nodes from anywhere in the graph, predict, or do nothing, and you can match trained Graph Neural Networks using a frozen LLM with zero fine-tuning.

MINGHAO GUO, XI ZHU, JINGYUAN HUANG, KAI MEI, YONGFENG ZHANG (RUTGERS UNIVERSITY) · 2025
Read
16 min
Source
arXiv:2508.00429