ToolOmni is a tool-use language model released for the ACL 2026 Main Conference paper ToolOmni: Enabling Open-World Tool Use via Agentic Learning with Proactive Retrieval and Grounded Execution. This checkpoint is built on top of Qwen/Qwen3-4B-Instruct and is designed for open-world tool use. The model is trained to proactively retrieve relevant tools and generate grounded multi-step tool calls for downstream task completion. — Model type: Causal language model for tool use — Base model: Qwen/Qwen3-4B-Instruct — Paper venue: ACL 2026 Main Conference — Codebase: training, evaluation, retrieval, and tool execution utilities are available in the public repository — research on tool-use agents — benchmarking open-world tool retrieval and grounded execution — studying retrieval-augmented and execution-aware training — reproducing the ToolOmni evaluation pipeline The model is expected to work best toget — proactive tool retrieval — grounded tool execution — reinforcement learning for multi-step tool-use behavior The training and evaluation pipeline is released in the ToolOmni repository. ToolOmni is evaluated on…
Модальности:
Генерация текста
Области применения:
Диалог / чат Вызов функций (Tool use) RAG (поиск + генерация)
Задача: Генерация текста
Автор: bue0912
Теги: qwen3, tool-use, agent, retrieval, reinforcement-learning, toolomni, conversational, en
Лайков: 4 | Загрузок: 57
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
