Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents

TL;DR

OpenTools is a community-driven framework that standardizes, evaluates, and monitors external tools for AI agents, significantly improving reliability and task performance through collective contributions.

Contribution

It introduces a standardized, extensible toolbox with evaluation pipelines and a contribution protocol, emphasizing intrinsic tool accuracy for better AI agent reliability.

Findings

Community contributions lead to 6%-22% performance gains.

Standardized evaluation improves reproducibility and reliability.

Intrinsic tool accuracy is crucial for effective tool use by AI agents.

Abstract

Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that failures stem from both tool-use accuracy (how well an agent invokes a tool) and intrinsic tool accuracy (the tool's own correctness), while most prior work emphasizes the former. We introduce OpenTools, a community-driven toolbox that standardizes tool schemas, provides lightweight plug-and-play wrappers, and evaluates tools with automated test suites and continuous monitoring. We also release a public web demo where users can run predefined agents and tools and contribute test cases, enabling reliability reports to evolve as tools change. OpenTools includes the core framework, an initial tool set, evaluation pipelines, and a contribution protocol. Experiments and evaluations show improved end-to-end reproducibility and task performance; community-contributed, higher-quality task-specific tools deliver 6%-22% relative gains over an existing toolbox across multiple agent architectures on downstream tasks and benchmarks, highlighting the importance of intrinsic tool accuracy.