This is the repository for the Tool Learning survey.
-
Updated
Sep 9, 2026
This is the repository for the Tool Learning survey.
[ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"
Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools
[ANON for Submission]
Auto tool retrieval for the Vercel AI SDK
Semantic tool retrieval for TypeScript agents, powered by Bun
Route predictable natural-language requests to deterministic workflows without using a generative LLM for the routing decision.
Tool retrieval and ranking algorithms for LLM agents with keyword, embedding, hybrid, decision-tree, and Gorilla-style selectors.
이 프로젝트는 OpenAI의 Function Calling 기능과 RAG(검색 증강 생성) 기술을 결합하여, 수많은 도구 라이브러리 중 질문에 가장 적합한 도구를 스스로 찾아 실행하는 지능형 에이전트 데모입니다.
Offline, zero-dependency MCP tool-router — funnel N tools to a ranked shortlist so your agent loads ~8, not 200. No embedding model, no network.
To associate your repository with the tool-retrieval topic, visit your repo's landing page and select "manage topics."