Saved in:
Bibliographic Details
Main Authors: Cheng, Zihang, Wang, Duanchu, Li, Cheng, Huang, Jing, Fu, Huanzhao, Wang, Di
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.27590
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914621370138624
author Cheng, Zihang
Wang, Duanchu
Li, Cheng
Huang, Jing
Fu, Huanzhao
Wang, Di
author_facet Cheng, Zihang
Wang, Duanchu
Li, Cheng
Huang, Jing
Fu, Huanzhao
Wang, Di
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27590
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes
Cheng, Zihang
Wang, Duanchu
Li, Cheng
Huang, Jing
Fu, Huanzhao
Wang, Di
Computer Vision and Pattern Recognition
Multimedia
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.
title ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2605.27590