让AI像科学家一样推理森林生态，还能留下可回放的思考过程。
ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes
- 用生态超图建模森林场景，支持多步逻辑推理
- 在复杂任务上准确率显著优于单步模型，执行一致性提升明显
- 适合需要可解释性生态分析的研究者与政策制定者
遥感问答（RS-QA）在大规模森林场景中需超越直接语义预测，涉及多步筛选、数值聚合、邻域推理和可验证证据。我们提出ForestHG-Trace框架，将多模态NEON森林场景表示为生态超图，包含树实例、空间单元、语义组及邻近关系，支持超越成对关系的高阶推理。基于LLM引导的智能体调用确定性工具完成读取、过滤、扩展、聚合、比较与审计，生成可回放的执行轨迹和紧凑证据记录，而非仅自由回答。我们构建了ForestTraceQA，一个可执行的基准测试，用于评估跨多种任务类型和推理深度的生态问答性能。实验表明，ForestHG-Trace在答案准确性和执行忠实度上显著优于单步基线与场景图代理，同时揭示执行深度是长时程生态问答的主要瓶颈。
原文摘要 · Abstract (English)
Remote sensing question answering (RS-QA) often requires more than direct semantic prediction, especially in large-scale forest scenes where ecological analysis involves multi-step filtering, numerical aggregation, neighborhood reasoning, and verifiable evidence. We introduce ForestHG-Trace, a framework for traceable long-horizon ecological reasoning over forest environments. It represents multimodal NEON forest scenes as ecological hypergraphs, where tree instances, spatial units, semantic groups, and neighborhood relations support higher-order reasoning beyond pairwise scene graphs. An LLM-guided agent then invokes deterministic tools for reading, filtering, expansion, aggregation, comparison, and auditing, producing replayable execution traces and compact evidence records rather than only free-form answers. We further construct ForestTraceQA, an executable benchmark for evaluating ecological QA across diverse task types and reasoning depths. Experiments show that ForestHG-Trace substantially improves answer accuracy and execution faithfulness over single-step baselines and scene-graph agents, while highlighting execution depth as the main bottleneck for long-horizon ecological QA.
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。