Graph Reasoning

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 41

All topics

Grokers: Bottom-Up Inductive Comprehension and Write-Time Intelligence over Typed Knowledge Graphs
May 7, 2026Gregory MagarshakKG Construction Memory-Augmented Language Models
Qbix, Inc. & Intercoin, Inc. · IE University NYC · New York, NY, USA
Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
May 2, 2026Sunil Kumar Maurya, Xin LiuLLM Evaluation LLM Reasoning with Graphs
University of Tokyo Tokyo, Japan · AIST Tokyo, Japan
Graph-based Semantic Calibration Network for Unaligned UAV RGBT Image Semantic Segmentation and A Large-scale Benchmark
Apr 29, 2026Fangqiang Fan, Zhicheng Zhao, Xiaoliang Ma +2Cross-Modal Alignment Graph Reasoning
Key Laboratory of Intelligent Computing & Signal Processing (Anhui University), Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Artificial Intelligence, Anhui University, Hefei 230601, China · School of Computer Science and Technology, Anhui University, Hefei 230601, China · GEOVIS Earth Technology Co., Ltd., Hefei 230088, China +1
Don't Make the LLM Read the Graph: Make the Graph Think
Apr 24, 2026Yuqi Sun, Tianqin Meng, George Liu +4Multi-Agent Coordination Game-Playing Agents
Mindoverflow · University of Waterloo · Carnegie Mellon University +4
Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation
Apr 23, 2026Hanwen Gu, Chao Guo, Junle Wang +2LLM Planning Graph-Based Planning
Institute of Automation, Chinese Academy of Sciences · Tencent Turing Lab
DW-Bench: Benchmarking LLMs on Data Warehouse Graph Topology Reasoning
Apr 21, 2026Ahmed G. A. H Ahmed, C. Okan SakarLLM Evaluation LLM Reasoning with Graphs
Innosol / Bahçe¸sehir University · Department of Computer Engineering, Bahcesehir University, Turkey
GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning
Apr 18, 2026Wenjin Li, Jiaming CuiMulti-Agent LLM Systems LLM Reasoning with Graphs
Department of Computer Science, Virginia Tech
Navigating Taxonomic Expansions of Entity Sets Driven by Knowledge Bases
Dec 17, 2025Giovanni Amendola, Pietro Cofone, Marco Manna +1Graph Reasoning Knowledge Graphs
University of Calabria, Rende, Italy · University of Cyprus, Nicosia, Cyprus
CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
Dec 11, 2025Shresth Grover, Priyank Pathak, Akash Kumar +1VLM Reasoning Visually Grounded Reasoning
UCF Institute of Artificial Intelligence, University of Central Florida (UCF)
GraphPilot: Grounded Scene Graph Conditioning for Language-Based Autonomous Driving
Nov 14, 2025Fabian Schmidt, Markus Enzweiler, Abhinav ValadaVision-Language Models VLMs for Autonomous Driving
Esslingen University of Applied Sciences · University of Freiburg
Fine-Grained Instruction-Guided Graph Reasoning for Vision-and-Language Navigation
Mar 14, 2025Yaohua Liu, Binkai Ou, Rong Fu +2Vision-Language Navigation Vision-Language Grounding
Faculty of Science and Technology, University of Macau, Macau 999078, China

May 7, 2026, cs.AIJ/K move · Enter open · S save

Grokers: Bottom-Up Inductive Comprehension and Write-Time Intelligence over Typed Knowledge Graphs

Gregory Magarshak

Qbix, Inc. & Intercoin, Inc. · IE University NYC · New York, NY, USA

KG Construction Memory-Augmented Language Models Knowledge Representation LLM Inference Acceleration Graph Reasoning Knowledge Graphs

Open paper AskPDF arXiv

We present Grokers, an architecture for building persistent, structured comprehension of typed knowledge graphs through bottom-up inductive traversal of dependency subgraphs. Unlike retrieval-augmented generation (RAG), which pays full comprehension cost at every query, Grokers pushes intelligence to write time: autonomous Groker agents analyze nodes in a typed stream graph, extract structured attributes via governed language model (LM) calls, and inductively compose that understanding upward through dependency relations, writing enriched typed attributes that serve all future queries at zero additional LM cost. We prove three formal properties: (1) the Byte-Identity Theorem, establishing that context blocks assembled from a transactionally-maintained denormalization index are byte-identical across LM turns between semantic changes, enabling KV-cache hit rates approaching 100%; (2) the Accumulation Monotonicity Theorem, establishing that the fraction of interactions resolved without LM calls is non-decreasing in the number of completed interactions under a governed wisdom library growth protocol; and (3) the Dual-Traversal Ordering Theorem, establishing that top-down generation and bottom-up comprehension are the unique correct traversal orderings for their respective tasks over a dependency DAG, and that their composition closes into a complete generation-comprehension cycle. We further present a deterministic alternative to embedding-based semantic search, with a synonym caching protocol whose LM fallback rate converges to zero for finite-vocabulary domains. A reference implementation is provided in the open-source Qbix / Safebox / Safebots stack.

Momentum

Related topics

Latest papers 41