DART-SD：面向多轮工具调用智能体自蒸馏的菱形拓扑感知检索与调优

DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

August 19, 2026

作者: Hangrui Xu, Jiarui Wang, Yang Yang, Chuanbo Zhu, Fangda Chen, Ziqi Wu, Jingming Cai, Yan Song

cs.AI

摘要

为大型语言模型（LLM）配备多轮工具调用能力是构建自主智能体的关键。然而，由于依赖完整轨迹模仿，进展从根本上受到限制。对于包含多个顺序无关子目标的任务，最优解空间会形成庞大的组合菱形格。若强行将这种丰富的拓扑结构压缩为单条整体轨迹，将导致严重的拓扑坍缩，不加区分地惩罚有效的替代探索，并严重降低策略多样性。为解决该问题，我们提出DART-SD（面向自蒸馏的菱形拓扑感知检索与微调），该新框架将范式从全局强制转变为拓扑引导的局部修正。DART-SD首先将执行过程建模为收敛的交互状态转移图（ISTG），忠实刻画成功与失败探索路径中固有的菱形拓扑。在自主推演（rollout）中，框架识别关键拓扑断点（CTB），并检索具有成功支持的恢复参考。最后，我们通过CTB引导的局部监督引入渐进式自蒸馏范式，确保训练损失仅在生成的恢复步骤上计算，同时严格保护有效推理前缀免受破坏性梯度更新的影响。在复杂多轮工具调用基准上的实验表明，DART-SD显著优于传统的完整轨迹基线方法。

English

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.