> [!Note] > This repository contains model weights and configuration files for Agents-A1 in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc. Agents‑A1 is a long-horizon agentic model from InternScience, built to scale heterogeneous agentic abilities across multiple domains including Long‑horizon Search, Engineering, Scientific Research, Instruction Following, and Tool-calling. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities. From the scaling of long-horizon trajectories, Agents‑A1 is trained with the assistance of a domain-grounded knowledge-action infrastructure that jointly constructs actions, observations, and verifier outcomes, turning the agent’s process into a trainable target. From the scaling of heterogeneous agent abilities, Agents‑A1 presents a three-stage training paradigm for building scalable general-purpose agentic model. First, we perform full-domain supervised fine-tuning to align the base model with broad agentic behaviors. Second, we train domain-level teacher models to capture specialized expertise in…
Модальности:
Генерация текста Компьютерное зрение
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: InternScience
Теги: qwen3_5, image-text-to-text, quantized, vlm, vision, agentic, conversational, endpoints_compatible
Лайков: 4 | Загрузок: 3,493
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
