Incremental ai system updates research reports with less cost
Incremental Open-Ended Deep Research with Structured Harness
Computation and Language
Summary
Research reports often need to be updated as new information appears, but most AI systems start fresh each time, which can be slow and costly. The authors introduce a new approach that treats a report like a growing document, updating only the parts that need changing or adding new details while keeping valid content. Their method uses a structured format to organize sections and evidence, making updates more efficient and coherent over time. Their experiments show that this incremental update system maintains quality while saving time and resources compared to starting over each time.
What this means in practice
- •For technical writing teams: Keep technical manuals and reports continuously updated with less rewrite effort by incrementally applying new research findings with structured support.
- •For knowledge management teams: Maintain evolving knowledge bases automatically by incrementally revising and expanding reports with up-to-date verified information.
Authors
Meilin Chen, Hongyuan Bao
Abstract
Existing Open-Ended Deep Research (OEDR) systems primarily generate reports from scratch, making them inefficient for scenarios where research reports need to be continuously maintained as new information emerges. We introduce \textbf{Incremental Open-Ended Deep Research (Incremental-OEDR)}, a research setting that treats a report as an evolving research state and incrementally updates it by preserving valid knowledge, revising outdated or incomplete content, and incorporating newly available information. To support this setting, we propose \textbf{Structured Harness}, which represents reports as structured collections of outlines, sections, and supporting evidence, and provides structured retrieval, a persistent structured evidence pool, and structured generation for selective report updating and evidence reuse. We further establish a temporal evaluation framework spanning ten years, with \emph{Single-Step Task} and \emph{Long-Chain Task} to evaluate incremental updates over both individual transitions and long-term update chains. Extensive Experiments on DeepResearch Bench and DeepConsult under both the Open-source Configuration (OC) and Proprietary Configuration (PC) show that Incremental-OEDR maintains competitive report quality while substantially improving report continuity and reducing research costs. As shown in Figure~\ref{fig:profile}, it achieves up to 0.51 higher content-level ROUGE-L F1, 0.63 higher outline-level EM F1, 33\% lower token consumption, and 61\% fewer search calls than OEDR on DeepResearch Bench. For more details, please refer to our project page: https://ioedr-project.github.io/.