ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes
This work addresses the need for verifiable multi-step reasoning in remote sensing QA for ecologists, but is domain-specific and incremental in its combination of existing techniques.
ForestHG-Trace introduces a framework for traceable long-horizon ecological reasoning in forest remote sensing QA, using ecological hypergraphs and LLM-guided deterministic tools. It achieves substantial improvements in answer accuracy and execution faithfulness over baselines on the new ForestTraceQA benchmark.
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.