AGENTS+GRAPH

Agents+Graph:

AI agents have become increasingly prominent, with LLM‑based agents introducing stronger capabilities for autonomous reasoning, planning, and interaction. A growing foundation of these systems is their reliance on graph‑structured data, including planning graphs, graph‑of‑thought structures, task dependency graphs, agent coordination graphs, tool calling graphs, and memory graphs, which collectively support planning, execution, tool invocation, and long‑term memory management. At the same time, AI agents can enhance graph data systems through automated database tuning, adaptive query optimization, natural language interfaces such as text2Cypher translation, and agent‑driven graph analytics. These developments create new opportunities for data management research, calling for algorithms, system architectures, and evaluation frameworks that jointly leverage agent capabilities and large‑scale graph computation. The “Agents+Graph” workshop provides a timely venue for advancing this emerging area by uniting researchers focused on LLMs, AI agents, graph data management, and graph machine learning in real‑world applications.

We solicit unpublished papers discussing issues and successes under the broad category of Graph Data for Agents, and Agents for Graph Data in the following areas (and beyond):

• Agent Interaction with Task Planning Graphs

• Agent Interaction with Task Execution Graphs

• Agent Interaction with Memory Graphs

• Graphs for Multi-agent Interaction

• Knowledge Graphs as Reasoning Guidelines, Refiners, & Validators

• Agents for Graph Reasoning

• Agents for Text2Cypher & Text2SPARQL

• Agents for Knowledge Graph Construction

Additionally, the paper must have a clear data management focus, e.g., discussing data management solution(s) such as (but not limited to):

• Agent-centric Data and Input Modeling

• Unified Vector & Graph Memory for Agent Retrieval

• Consistency & Safety via Graph-grounded Reasoning

• Explainability, Provenance, & Benchmarking for Agentic Graph Reasoning

Submission Details:

We solicit and select five types of papers

• Survey Papers: these papers survey the related work in specific sub-areas and lay out the agenda for future work.

• Regular Research Papers: these are research papers with different flavors including foundations, algorithms, systems, information system architectures, experimental benchmarking, and applications. Papers with new/ late-breaking results are also welcome, which report the newest preliminary results about the most promising problems in the field.

• Vision Papers: these papers are devoted to discussing problems that we face currently and anticipate for the future.

• Demonstration Papers: these are software demonstration proposals, accompanied by short papers. The paper must describe the demonstrated system, user interface, options for user interactions, the system setup, and state the novelty and significance. We encourage providing the online link of a demonstration video, which is accessible by the reviewers.

• Extended Abstract Papers: if your research article has been accepted elsewhere, you are eligible to submit your work in the form of an extended abstract under the short paper category, while citing your previously published article. We encourage you to rephrase when needed or possible to avoid substantial verbatim text overlapping with past accepted/ published materials.

For survey, vision, demonstration, and extended abstract papers, you require to add [Survey], [Vision], [Demo], [Extended Abstract], respectively, next to the paper title, in both CMT submission form and also in the submitted paper pdf. We welcome the papers that fall under short papers of at most 6 pages and long papers up to 12 pages, including bibliography. Submissions must use the template at: vldb-workshop-style-master.zip. All submissions must be submitted in PDF through: https://cmt3.research.microsoft.com/AG2026/. Submissions will be reviewed in a single-blind manner, and all author names and affiliations should be included. Papers that do not follow the guidelines or are not within the scope of relevant topics will be desk rejected. We also expect that publications from DB venues, e.g., SIGMOD/VLDB/ICDE/EDBT etc. are cited. Submissions will be reviewed by at least three members of the Program Committee. All accepted papers will be published in VLDB workshop proceedings. The workshop will be in-person and at least one author of each accepted paper is required to register.