Abstract:Every LLM tool call is structurally an RPC -- a function name, JSON arguments, and a serialized result -- yet each protocol (native Python, MCP, OpenAPI, LangChain) is integrated from scratch. We present ToolRegistry, a system that makes this RPC nature explicit: a single Tool object acts as a universal stub regardless of transport, while the registry serves as the RPC client runtime for dispatch, schema generation, and execution. The system ships as three packages -- a core registry, a server exposing tools over MCP and OpenAPI, and a hub of production-ready implementations -- and invokes tools through pluggable thread or process backends. The system now also provides tag-based permission policies, BM25F-powered progressive tool disclosure for large registries, think-augmented function calling, multi-provider schema support (OpenAI, Anthropic, Gemini), declarative JSONC/YAML configuration, and a near-zero-dependency core built on stdlib-only vendored modules. In our benchmarks the library cuts integration code by 60-80%, and choosing the right concurrency mode (thread vs. process) yields up to 3.1x throughput over the alternative for a given workload. ToolRegistry is open-source at this https URL documentation lives at this https URL.
| Comments: | 16 pages, 4 figures, v3: add co-author, permission system, progressive tool disclosure, think-augmented calling, RPC framing, multi-provider support |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2507.10593 [cs.SE] |
| (or arXiv:2507.10593v3 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2507.10593 arXiv-issued DOI via DataCite |
From: Peng Ding [view email]
[v1]
Fri, 11 Jul 2025 20:23:23 UTC (138 KB)
[v2]
Wed, 18 Mar 2026 14:23:55 UTC (163 KB)
[v3]
Sun, 24 May 2026 23:49:32 UTC (157 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。