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

2025-07-14

AI Summary

To address insufficient retrieval diversity and limited controllability of analytical depth and breadth in ecological literature synthesis, this paper proposes a recursive agent workflow grounded in large language models (LLMs). The method introduces a parameterized control mechanism to dynamically adjust the depth and breadth of systematic reviews and integrates a domain-adapted evidence aggregation algorithm to ensure transparent, reproducible scientific synthesis. Distinct from conventional retrieval-augmented generation (RAG) paradigms, our framework pioneers the application of recursive agent architectures to intelligent ecological literature exploration—thereby substantially enhancing retrieval diversity and analytical granularity. Empirical evaluation across 49 real-world ecological research questions demonstrates that the approach achieves a 14.9× increase in integrated literature volume per thousand words and up to a 21× rise in total citations; under high-parameter configurations, its analytical depth matches expert-level performance.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

We introduce DeepResearch$^{ ext{Eco}}$, 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.

Problem

• Automates scientific synthesis for ecological research questions
• Enhances literature search diversity and analytical depth
• Improves source integration and contextual diversity

Innovation

• Recursive agentic workflow for scientific synthesis
• User-controllable synthesis with transparent reasoning
• Parameter-driven configurability for analytical rigor