{"ID":2894993,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.10522","arxiv_id":"2507.10522","title":"DeepResearch$^{\\text{Eco}}$: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecology","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.","short_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...","url_abs":"https://arxiv.org/abs/2507.10522","url_pdf":"https://arxiv.org/pdf/2507.10522v1","authors":"[\"Jennifer D'Souza\",\"Endres Keno Sander\",\"Andrei Aioanei\"]","published":"2025-07-14T17:47:28Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.MA\"]","methods":"[\"RAG\",\"Large Language Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":612147,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2894993,"paper_url":"https://arxiv.org/abs/2507.10522","paper_title":"DeepResearch$^{\\text{Eco}}$: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecology","repo_url":"https://github.com/sciknoworg/deep-research","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}