Search papers, labs, and topics across Lattice.
The paper introduces ForestHG-Trace, a framework for traceable long-horizon reasoning in remote sensing question answering (RS-QA) over large-scale forest scenes. It represents multimodal NEON forest data as ecological hypergraphs and uses an LLM-guided agent to invoke deterministic tools for reasoning steps like filtering and aggregation. Experiments on the new ForestTraceQA benchmark show that ForestHG-Trace significantly improves answer accuracy and execution faithfulness compared to baselines, while identifying execution depth as a key bottleneck.
LLMs can now perform traceable, multi-step ecological reasoning over complex forest environments by operating on ecological hypergraphs and invoking deterministic tools, achieving higher accuracy and faithfulness than single-step approaches.
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.