Built on

Neo4j graph database & analytics | graph database management
Neo4j. 2007 · 2007
Earlier work this paper cites.
The Probabilistic Relevance Framework: BM25 and Beyond
Stephen Robertson and Hugo Zaragoza. 2009 · 2009
Earlier work this paper cites.
Leveraging semantic and lexical matching to improve the recall of document retrieval systems: A hybrid approach
Original
Saar Kuzi, Mingyang Zhang, Cheng Li, Michael Bendersky, and Marc Najork. 2020 · 2010
Earlier work this paper cites.
ProTIP: Progressive Tool Retrieval Improves Planning
Original
Raviteja Anantha, Bortik Bandyopadhyay, Anirudh Kashi, Sayantan Mahinder, Andrew W. Hill, and Srinivas Chappidi. 2023 · 2023
Earlier work this paper cites.
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Original
Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023 · 2023
Earlier work this paper cites.
Diffkg: Knowledge graph diffusion model for recommendation
Original
Yangqin Jiang, Yuhao Yang, Lianghao Xia, and Chao Huang. 2023 · 2023
Earlier work this paper cites.
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
Original
Omar Khattab, Keshav Santhanam, Xiang Lisa Li, David Hall, Percy Liang, Christopher Potts, and Matei Zaharia. 2023 · 2023
Earlier work this paper cites.
How to use the parent document retriever
Langchain. 2023 · 2023
Earlier work this paper cites.
API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
Original
Minghao Li, Yingxiu Zhao, Bowen Yu, Feifan Song, Hangyu Li, Haiyang Yu, Zhoujun Li, Fei Huang, and Yongbin Li. 2023 · 2023
Earlier work this paper cites.
Controlllm: Augment language models with tools by searching on graphs
Original
Zhaoyang Liu, Zeqiang Lai, Zhangwei Gao, Erfei Cui, Ziheng Li, Xizhou Zhu, Lewei Lu, Qifeng Chen, Yu Qiao, Jifeng Dai, and Wenhai Wang. 2023 · 2023
Earlier work this paper cites.
Query Rewriting for Retrieval-Augmented Large Language Models
Original
Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, and Nan Duan. 2023 · 2023
Earlier work this paper cites.
Azure ai search
Microsoft. 2023 · 2023
Earlier work this paper cites.
Toolllm: Facilitating large language models to master 16000+ real-world apis
Original
Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou, Mark Gerstein, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2023 · 2023
Earlier work this paper cites.
Forget RAG, the future is RAG-Fusion: The next frontier of search: Retrieval Augmented Generation meets Reciprocal Rank Fusion and generated queries
A. H. Raudaschl. 2023 · 2023
Earlier work this paper cites.
A benchmark to understand the role of knowledge graphs on large language model’s accuracy for question answering on enterprise sql databases
Original
Juan Sequeda, Dean Allemang, and Bryon Jacob. 2023 · 2023
Earlier work this paper cites.
Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
Original
Weiwei Sun, Lingyong Yan, Xinyu Ma, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, and Zhaochun Ren. 2023 · 2023
Earlier work this paper cites.
Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
Original
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023 · 2023
Earlier work this paper cites.

Similar

ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Original
Binfeng Xu, Zhiyuan Peng, Bowen Lei, Subhabrata Mukherjee, Yuchen Liu, and Dongkuan Xu. 2023 · 2023
Cited alongside, same era.
Advanced rag 01: Small-to-big retrieval
Sophia Yang. 2023 · 2023
Cited alongside, same era.
ReAct: Synergizing Reasoning and Acting in Language Models
Original
Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023 · 2023
Cited alongside, same era.
Graph-toolformer: To empower llms with graph reasoning ability via prompt augmented by chatgpt
Original
Jiawei Zhang. 2023 · 2023
Cited alongside, same era.
Introducing contextual retrieval
Anthropic. 2024 · 2024
Cited alongside, same era.

Then

Toolnet: Connecting large language models with massive tools via tool graph
Original
Xukun Liu, Zhiyuan Peng, Xiaoyuan Yi, Xing Xie, Lirong Xiang, Yuchen Liu, and Dongkuan Xu. 2024 · 2024
Later among the works it cites.
Toolsandbox: A stateful, conversational, interactive evaluation benchmark for llm tool use capabilities
Original
Jiarui Lu, Thomas Holleis, Yizhe Zhang, Bernhard Aumayer, Feng Nan, Felix Bai, Shuang Ma, Shen Ma, Mengyu Li, Guoli Yin, Zirui Wang, and Ruoming Pang. 2024 · 2024
Later among the works it cites.
Toolshed: Scale tool-equipped agents with advanced rag-tool fusion and tool knowledge bases
Original
Elias Lumer, Vamse Kumar Subbiah, James A. Burke, Pradeep Honaganahalli Basavaraju, and Austin Huber. 2024 · 2024
Later among the works it cites.
Efficient and Scalable Estimation of Tool Representations in Vector Space
Original
Suhong Moon, Siddharth Jha, Lutfi Eren Erdogan, Sehoon Kim, Woosang Lim, Kurt Keutzer, and Amir Gholami. 2024 · 2024
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2025

Graph RAG-Tool Fusion

Lumer, Elias, Basavaraju, Pradeep Honaganahalli, Mason, Myles et al.

Understand

Recent developments in retrieval-augmented generation (RAG) for selecting relevant tools from a tool knowledge base enable LLM agents to scale their complex tool calling capabilities to hundreds or thousands of external tools, APIs, or agents-as-tools.

However, traditional RAG-based tool retrieval fails to capture structured dependencies between tools, limiting the retrieval accuracy of a retrieved tool's dependencies.
For example, among a vector database of tools, a "get stock price" API requires a "stock ticker" parameter from a "get stock ticker" API, and both depend on OS-level internet connectivity tools.
In this paper, we address this limitation by introducing Graph RAG-Tool Fusion, a novel plug-and-play approach that combines the strengths of vector-based retrieval with efficient graph traversal to capture all relevant tools (nodes) along with any nested dependencies (edges) within the predefined tool knowledge graph.