mlsanityData to 14 Oct 2026

GDS Agent for Graph Algorithmic Reasoning

arXiv 2508.20637 ↗First posted 28 Aug 2025cs.LG cs.AI cs.CLcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

Large language models (LLMs) have shown remarkable multimodal information processing and reasoning ability. When equipped with tools through function calling and enhanced with retrieval-augmented techniques, compound LLM-based systems can access closed data sources and answer questions about them. However, they still struggle to process and reason over large-scale graph-structure data. We introduce the GDS (Graph Data Science) agent in this technical report. The GDS agent introduces a comprehensive set of graph algorithms as tools, together with preprocessing (retrieval) and postprocessing of algorithm results, in a model context protocol (MCP) server. The server can be used with any modern LLM out-of-the-box. GDS agent allows users to ask any question that implicitly and intrinsically requires graph algorithmic reasoning about their data, and quickly obtain accurate and grounded answers. We introduce new benchmarks that evaluate intermediate tool calls as well as final responses. The results indicate that GDS agent is able to solve a wide spectrum of graph tasks. We also provide detailed case studies for more open-ended tasks and study scenarios where the agent struggles. Finally, we discuss the remaining challenges and the future roadmap.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 12 of its 34 references that are in the map. First posted on arXiv 28 Aug 2025.

Builds on

12 of 34 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases7 Apr
  2. 2024Are Large-Language Models Graph Algorithmic Reasoners?29 Oct

Other references · 10

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  7. 2023Talk like a Graph: Encoding Graphs for Large Language Modelscited by 176
  8. 2025Agentic Large Language Models, a surveycited by 108
  9. 2024The CLRS-Text Algorithmic Reasoning Language Benchmarkcited by 28
  10. 2024GQL and SQL/PGQ: Theoretical Models and Expressive Powercited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs
  2. 2024Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents
  3. 2026GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning
  4. 2026Are Large Language Models Suitable for Graph Computation? Progress and Prospects
  5. 2025Rethinking and Benchmarking Large Language Models for Graph Reasoning
  6. 2025GR-Agent: Adaptive Graph Reasoning Agent under Incomplete Knowledge
  7. 2025Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving
  8. 2023Graph Agent: Explicit Reasoning Agent for Graphs