用专家规则与视觉语言模型协作，自动标注树木高度偏差，大幅降低人工标注成本。
TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models
- 用决策树作结构先验，VLM在节点做语义感知，多智能体投票减少随机性。
- 在树高偏差分类任务中超越监督学习基线，标注成本显著降低。
- 适合需要可解释标注的林业遥感领域，尤其适用于专家规则多样场景。
人工标注数据在机器学习中广泛用作参考标注，但在许多专家驱动领域中存在标注者间差异。此外，专家标注速度慢、不一致，已成为林业遥感中树高偏差分类等任务规模化的主要瓶颈。我们提出一种多智能体系统（MAS），将专家决策树与视觉语言模型（VLMs）协同，以决策树作为结构先验，由VLM在各节点执行局部语义感知，并通过多智能体投票缓解VLM的随机性。我们形式化了一种解耦式声明式决策（D3）框架，实现对不同专家定义决策结构的零修改泛化。在树高偏差分类测试平台上，该框架优于监督学习基线，并显著减少所需专家标注量。结果表明，通过智能体协同整合VLM与专家先验，可在大幅降低标注成本的同时复现专家标注流程并保持可解释性。
原文摘要 · Abstract (English)
Human-labeled data are widely used as reference annotations in ML, despite known variability across annotators in many expert-driven domains. In addition, expert annotation is slow, inconsistent, and remains a major bottleneck for scaling tasks like tree height bias classification in forestry remote sensing. We propose a multi-agent system (MAS) that orchestrates expert decision trees with Vision-Language Models (VLMs), treating the decision tree as a structural prior while VLMs perform localized semantic perception at individual nodes, with multi-agent voting to mitigate VLM stochasticity. We formalize a Decoupled Declarative Decision (D3) Framework that enables zero-modification generalization across diverse expert-defined decision structures. On a tree bias classification testbed, our framework outperforms supervised ML baselines and reduces the amount of expert labeling effort required. These results suggest that agentic orchestration of VLMs with expert priors can reproduce expert-defined labeling procedures at substantially lower annotation cost while maintaining interpretability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。