阿特拉斯：面向多领域复杂推理的异构模型与工具编排框架

摘要

大型语言模型（LLMs）与外部工具的融合显著拓展了智能体的能力边界。然而，随着模型与工具多样性的同步增长，选择最优的模型-工具组合已成为高维优化难题。现有方案通常依赖单一模型或固定工具调用逻辑，未能充分利用异构模型-工具组合间的性能差异。本文提出ATLAS（自适应工具-LLM对齐与协同调用框架），这是一种面向跨领域复杂推理的动态工具调用双路径架构。该框架通过双路径机制运作：（1）基于无训练聚类路由的领域适配路径，利用经验先验实现领域特异性对齐；（2）基于强化学习的多步路由路径，通过自主轨迹探索实现分布外泛化。在15个基准测试上的大规模实验表明，我们的方法在分布内任务（+10.1%）和分布外任务（+13.1%）上均超越GPT-4o等闭源模型，显著优于现有路由方案。此外，通过协调专用多模态工具，本框架在视觉推理任务中展现出显著优势。

English

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a high-dimensional optimization challenge. Existing approaches often rely on a single model or fixed tool-calling logic, failing to exploit the performance variations across heterogeneous model-tool pairs. In this paper, we present ATLAS (Adaptive Tool-LLM Alignment and Synergistic Invocation), a dual-path framework for dynamic tool usage in cross-domain complex reasoning. ATLAS operates via a dual-path approach: (1) training-free cluster-based routing that exploits empirical priors for domain-specific alignment, and (2) RL-based multi-step routing that explores autonomous trajectories for out-of-distribution generalization. Extensive experiments across 15 benchmarks demonstrate that our method outperforms closed-source models like GPT-4o, surpassing existing routing methods on both in-distribution (+10.1%) and out-of-distribution (+13.1%) tasks. Furthermore, our framework shows significant gains in visual reasoning by orchestrating specialized multi-modal tools.

阿特拉斯：面向多领域复杂推理的异构模型与工具编排框架

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

摘要

Support