Incremental Open-Ended Deep Research with Structured Harness

Key points

• 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.1
• To support this setting, we propose 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.1
• We further establish a temporal evaluation framework spanning ten years, with Single-Step Task and Long-Chain Task to evaluate incremental updates over both individual transitions and long-term update chains.1
• 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.1

Sources (2)

• [1]Incremental Open-Ended Deep Research with Structured Harness
  Hugging Face Daily Papers · Oct 8, 12:00 AM

  We introduce 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that treats a report as an evolving research state and incrementally updates it by preserving valid knowledge, revising outdated or incomplete content, and incorporating newly available information.

  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.

• [2]Incremental Open-Ended Deep Research with Structured Harness
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 09:24 AM · same content

Extractive summary: sentences quoted from the sources.