DeepResearch$^{\text{Eco}}$: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecology
This addresses the need for efficient and nuanced literature retrieval and synthesis in ecology, offering a scalable solution for researchers, though it appears incremental as an enhancement over existing retrieval-augmented generation pipelines.
The paper tackles the problem of automated scientific synthesis for complex ecological questions by introducing DeepResearch$^{\text{Eco}}$, a novel agentic LLM-based system that achieves up to a 21-fold increase in source integration and a 14.9-fold rise in sources per 1,000 words compared to conventional methods.
We introduce DeepResearch$^{\text{Eco}}$, a novel agentic LLM-based system for automated scientific synthesis that supports recursive, depth- and breadth-controlled exploration of original research questions -- enhancing search diversity and nuance in the retrieval of relevant scientific literature. Unlike conventional retrieval-augmented generation pipelines, DeepResearch enables user-controllable synthesis with transparent reasoning and parameter-driven configurability, facilitating high-throughput integration of domain-specific evidence while maintaining analytical rigor. Applied to 49 ecological research questions, DeepResearch achieves up to a 21-fold increase in source integration and a 14.9-fold rise in sources integrated per 1,000 words. High-parameter settings yield expert-level analytical depth and contextual diversity. Source code available at: https://github.com/sciknoworg/deep-research.