Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2604.00137 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917375848218624 |
|---|---|
| author | Dang, Hy Dao, Quang Jiang, Meng |
| author_facet | Dang, Hy Dao, Quang Jiang, Meng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00137 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents Dang, Hy Dao, Quang Jiang, Meng Artificial Intelligence Software Engineering 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. |
| title | Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents |
| topic | Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2604.00137 |