ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes

Researchers have developed ForestHG-Trace, a framework enabling traceable long-horizon ecological reasoning over large-scale forest scenes by representing multimodal NEON forest data as ecological hypergraphs. The system uses an LLM-guided agent to invoke deterministic tools for multi-step filtering, aggregation, and auditing, producing replayable execution traces and compact evidence records. In evaluations using the new ForestTraceQA benchmark, ForestHG-Trace significantly improved answer accuracy and execution faithfulness over single-step and scene-graph baselines, with execution depth identified as the primary bottleneck for complex ecological question answering.

arXiv:2605.27590v1 Announce Type: new Abstract: 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.