AI 学工具调用，别再整段照抄了
训练 AI 学会多步调用工具，过去是让它照着人类示范的完整流程一步步模仿。但很多任务里，中间步骤的顺序其实可以打乱，就像先放盐还是先放糖都能做出菜。硬套一条固定流程，AI 一旦走岔一步就被判错，反而不敢探索新路。这篇研究把执行过程画成一张图，只盯着 AI 走错的那个关键节点，用成功案例教它怎么绕回来，其余正确的推理步骤则原样保留。在复杂工具调用测试上，效果明显好过整段模仿的老办法。它不是你明天就能用上的功能，但指向了训练 AI 更聪明、更灵活的方向。
📄 原文摘要(英文)
Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fundamentally limited by the reliance on full-length trajectory imitation. For tasks involving multiple order-independent sub-goals, the optimal solution space forms a vast combinatorial diamond lattice. Forcing this rich topology into monolithic trajectories causes a severe topological collapse, indiscriminately penalizing valid alternative explorations and severely degrading policy diversity. To address this, we propose DART-SD (Diamond-topology Aware Retrieval and Tuning for Self-Distillation), a novel framework that shifts the paradigm from global forcing to topology-guided localized correction. DART-SD first models the execution process as a converging Interaction-State Transition Graph (ISTG), faithfully capturing the inherent diamond topology of successful and failed exploratory paths. During autonomous rollouts, the framework identifies the Critical Topological Breakpoint (CTB) and retrieves success-supported recovery references. Finally, we introduce a progressive self-distillation paradigm through CTB-guided localized supervision, ensuring that the training loss is calculated exclusively on the generated recovery steps while strictly protecting the valid reasoning prefix from destructive gradient updates. Experiments on complex multi-turn tool-calling benchmarks demonstrate that DART-SD significantly outperforms traditional full-trajectory baselines.