CamAgent：用于多物种相机陷阱工作流的LLM智能体框架

中文摘要 AI 辅助

相机陷阱积累了用于野生动物监测的海量多维数据，但将原始媒体档案转化为有意义的生态学见解仍高度碎片化。当前的研究工作流需要费力地拼接不同的分析工具和脚本，造成陡峭的编程障碍，并使端到端的时空分析复杂化。为克服这种碎片化，我们提出了CamAgent，一个自主的大语言模型（LLM）智能体框架，将相机陷阱分析工作流整合为一个统一的智能生态系统。CamAgent解释自然语言生态学意图，调度计算路由，并执行涵盖计算机视觉感知（如SpeciesNet）、兼容CamtrapDP的数据管理、检测校正的占用模型、时间活动分析以及物种共现网络的专业工具。该框架自动化多阶段分析流水线，同时保持关键的数据质量控制和分析惯例。因此，CamAgent显著减少了保护工作者的手动编程开销，为相机陷阱生态学建立了一个透明、可扩展且完全集成的范式。我们的项目可在以下网址获取：此https URL。

英文摘要

Camera traps accumulated vast, multidimensional data for wildlife monitoring, yet translating raw media archives into meaningful ecological insights remains highly fragmented. Current research workflows require laboriously stitching together disparate analysis tools and scripts, creating steep programming hurdles and complicating end-to-end spatiotemporal analyses. To overcome this fragmentation, we present CamAgent, an autonomous Large Language Model (LLM) agent framework that integrates camera-trap analytical workflows into a unified intelligent ecosystem. CamAgent interprets natural-language ecological intent, schedules computational routing, and executes specialized tools spanning computer-vision perception (e.g., SpeciesNet), CamtrapDP-compatible data management, detection-corrected occupancy modeling, temporal activity analysis, and species co-occurrence networks. The framework automates multi-stage analytical pipelines while maintaining essential data-quality controls and analytical conventions. Consequently, CamAgent significantly reduces manual programming overhead for conservationists, establishing a transparent, scalable, and fully integrated paradigm for camera-trap ecology. Our project is available at https://anonymous.4open.science/r/artifact72c6f4.

发表机构

• Beijing Normal University（北京师范大学）
• National Forestry and Grassland Administration Key Laboratory for Conservation Ecology of Northeast Tiger and Leopard（国家林业和草原局东北虎豹保护生态学重点实验室）

机构由 AI 辅助整理，请以论文原文为准。