ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs

• URL: http://arxiv.org/abs/2507.10593v1
• Date: Fri, 11 Jul 2025 20:23:23 GMT
• Title: ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
• Abstract summary: toolregistry is a protocol-agnostic tool management library that simplifies tool registration, representation, execution, and lifecycle management.<n>toolregistry achieves 60-80% reduction in tool integration code, up to 3.1x performance improvements through concurrent execution, and 100% compatibility with OpenAI function calling standards.
• Score: 1.3830651939939742
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Model (LLM) applications are increasingly relying on external tools to extend their capabilities beyond text generation. However, current tool integration approaches suffer from fragmentation, protocol limitations, and implementation complexity, leading to substantial development overhead. This paper presents Toolregistry, a protocol-agnostic tool management library that simplifies tool registration, representation, execution, and lifecycle management via a unified interface. Our evaluation demonstrates that \toolregistry achieves 60-80% reduction in tool integration code, up to 3.1x performance improvements through concurrent execution, and 100% compatibility with OpenAI function calling standards. Real-world case studies show significant improvements in development efficiency and code maintainability across diverse integration scenarios. \toolregistry is open-source and available at https://github.com/Oaklight/ToolRegistry, with comprehensive documentation at https://toolregistry.readthedocs.io/.

Related papers

• VeriAgent: A Tool-Integrated Multi-Agent System with Evolving Memory for PPA-Aware RTL Code Generation [52.43796056267479]
  We propose a PPA-aware, tool-integrated multi-agent framework for high-quality verilog code generation.<n>Our framework explicitly incorporates EDA tools into a closed-loop workflow composed of a textitProgrammer Agent, a textitCorrectness Agent, and a textitPPA Agent<n>To support continuous improvement without model retraining, we introduce an textitEvolved Memory Mechanism that externalizes optimization experience into structured memory nodes.
  arXiv  Detail & Related papers  (2026-03-18T11:25:40Z)
• ToolRosetta: Bridging Open-Source Repositories and Large Language Model Agents through Automated Tool Standardization [51.92237664440418]
  ToolRosetta is a framework that automatically translates open-source code repositories and APIs into MCP-compatible tools.<n>Given a user task, ToolRosetta autonomously plans toolchains, identifies relevant toolchains, and converts them into executable MCP services.
  arXiv  Detail & Related papers  (2026-03-10T07:19:43Z)
• OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction [41.38214226411103]
  Tool-calling is essential for Large Language Model (LLM) agents to complete real-world tasks.<n>While most existing benchmarks assume simple, perfectly documented tools, real-world tools are often opaque, lacking clear best practices or failure modes.<n>We propose ToolObserver, that iteratively refines tool documentation by observing execution feedback from tool-calling trajectories.
  arXiv  Detail & Related papers  (2026-02-16T21:26:37Z)
• DeepAgent: A General Reasoning Agent with Scalable Toolsets [111.6384541877723]
  DeepAgent is an end-to-end deep reasoning agent that performs autonomous thinking, tool discovery, and action execution.<n>To address the challenges of long-horizon interactions, we introduce an autonomous memory folding mechanism that compresses past interactions into structured episodic, working, and tool memories.<n>We develop an end-to-end reinforcement learning strategy, namely ToolPO, that leverages LLM-simulated APIs and applies tool-call advantage attribution to assign fine-grained credit to the tool invocation tokens.
  arXiv  Detail & Related papers  (2025-10-24T16:24:01Z)
• Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use [50.02614257515131]
  Large language models (LLMs) have demonstrated strong capabilities in language understanding and reasoning.<n>We propose Tool-R1, a reinforcement learning framework that enables LLMs to perform general, compositional, and multi-step tool use.
  arXiv  Detail & Related papers  (2025-09-16T09:22:21Z)
• Automated Creation and Enrichment Framework for Improved Invocation of Enterprise APIs as Tools [10.440520289311332]
  ACE is an automated tool creation and enrichment framework for Large Language Models.<n>It generates enriched tool specifications with parameter descriptions and examples to improve selection and invocation accuracy.<n>We validate our framework on both proprietary and open-source APIs and demonstrate its integration with agentic frameworks.
  arXiv  Detail & Related papers  (2025-09-15T06:41:54Z)
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use [78.29315418819074]
  We introduce VerlTool, a unified and modular framework that addresses limitations through systematic design principles.<n>Our framework formalizes ARLT as multi-turn trajectories with multi-modal observation tokens (text/image/video), extending beyond single-turn RLVR paradigms.<n>The modular plugin architecture enables rapid tool integration requiring only lightweight Python definitions.
  arXiv  Detail & Related papers  (2025-09-01T01:45:18Z)
• Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling [1.2935057904849891]
  Large Language Models (LLMs) have created a fragmented ecosystem where developers must navigate multiple protocols.<n>We propose a unified approach to tool integration that abstracts protocol differences while optimizing execution performance.
  arXiv  Detail & Related papers  (2025-08-05T01:06:49Z)
• Designing and Implementing Robust Test Automation Frameworks using Cucumber BDD and Java [0.0]
  This paper details a comprehensive approach to designing and implementing robust test automation frameworks.<n>By utilizing Cucumber BDD natural language syntax, the framework enables clear communication between technical and non-technical team members.<n>Java serves as the backbone for creating scalable, maintainable, and efficient test scripts.
  arXiv  Detail & Related papers  (2025-05-22T17:11:05Z)
• PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play [24.784100934155237]
  Large language models (LLMs) are increasingly integrated with specialized external tools.<n>Many tasks demand zero-shot tool usage with minimal or noisy documentation.<n>We propose PLAY2PROMPT, an automated framework that systematically "plays" with each tool to explore its input-output behaviors.
  arXiv  Detail & Related papers  (2025-03-18T17:09:57Z)
• LLM Agents Making Agent Tools [2.5529148902034637]
  Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks.<n>But these tools must be implemented in advance by human developers.<n>We propose ToolMaker, an agentic framework that autonomously transforms papers with code into LLM-compatible tools.
  arXiv  Detail & Related papers  (2025-02-17T11:44:11Z)
• Commit0: Library Generation from Scratch [77.38414688148006]
  Commit0 is a benchmark that challenges AI agents to write libraries from scratch.<n>Agents are provided with a specification document outlining the library's API as well as a suite of interactive unit tests.<n> Commit0 also offers an interactive environment where models receive static analysis and execution feedback on the code they generate.
  arXiv  Detail & Related papers  (2024-12-02T18:11:30Z)
• Towards Completeness-Oriented Tool Retrieval for Large Language Models [60.733557487886635]
  Real-world systems often incorporate a wide array of tools, making it impractical to input all tools into Large Language Models. Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions. We propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
  arXiv  Detail & Related papers  (2024-05-25T06:41:23Z)
• EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction [56.02100384015907]
  EasyTool is a framework transforming diverse and lengthy tool documentation into a unified and concise tool instruction. It can significantly reduce token consumption and improve the performance of tool utilization in real-world scenarios.
  arXiv  Detail & Related papers  (2024-01-11T15:45:11Z)
• ControlLLM: Augment Language Models with Tools by Searching on Graphs [97.62758830255002]
  We present ControlLLM, a novel framework that enables large language models (LLMs) to utilize multi-modal tools for solving real-world tasks. Our framework comprises three key components: (1) a textittask decomposer that breaks down a complex task into clear subtasks with well-defined inputs and outputs; (2) a textitThoughts-on-Graph (ToG) paradigm that searches the optimal solution path on a pre-built tool graph; and (3) an textitexecution engine with a rich toolbox that interprets the solution path and runs the
  arXiv  Detail & Related papers  (2023-10-26T21:57:21Z)
• Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding [11.51687663492722]
  Large language models (LLMs) excel at many tasks but often fail to use external tools due to complicated and unfamiliar syntax constraints. We propose TOOLDEC, a decoding algorithm using finite state machines to force LLMs to follow tool syntax. Experiments show that TOOLDEC eliminates all syntax errors, achieving significantly better performance on various base models and benchmarks.
  arXiv  Detail & Related papers  (2023-10-10T23:37:53Z)
• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs [104.37772295581088]
  Open-source large language models (LLMs), e.g., LLaMA, remain significantly limited in tool-use capabilities. We introduce ToolLLM, a general tool-usetuning encompassing data construction, model training, and evaluation. We first present ToolBench, an instruction-tuning framework for tool use, which is constructed automatically using ChatGPT.
  arXiv  Detail & Related papers  (2023-07-31T15:56:53Z)
• ART: Automatic multi-step reasoning and tool-use for large language models [105.57550426609396]
  Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings. Each reasoning step can rely on external tools to support computation beyond the core LLM capabilities. We introduce Automatic Reasoning and Tool-use (ART), a framework that uses frozen LLMs to automatically generate intermediate reasoning steps as a program.
  arXiv  Detail & Related papers  (2023-03-16T01:04:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.