DeepResearch$^{\text{Eco}}$: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecology

TL;DR

DeepResearch$^{\text{Eco}}$ is an innovative agentic system leveraging large language models for automated, recursive scientific synthesis in ecology, significantly improving literature integration and analytical depth for complex research questions.

Contribution

It introduces a controllable, transparent, and recursive LLM-based framework for ecological research synthesis, surpassing traditional retrieval methods in diversity and depth.

Findings

Up to 21-fold increase in source integration

14.9-fold more sources per 1,000 words

Achieves expert-level analytical depth with high-parameter settings

Abstract

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.