Tag
We introduce CohortFlow, a steerable LLM agent for clinical cohort curation that applies natural language corrections as localized updates to a structured specification, preserving unaffected computations via explicit semantic dependencies. It matches full-regeneration accuracy while reducing correction latency by 64.8% and model calls by 38.1%.
本文提出 Incremental Open-Ended Deep Research（Incremental-OEDR）研究设定与 Structured Harness 框架，将研究报告视为可随新信息持续演化的结构化状态，在保持报告质量的同时显著降低研究成本（token 消耗减少 33%，搜索调用减少 61%）。
An analysis questioning why progress on Deep Research AI products has stalled since their impressive launch in February 2025, noting that known weaknesses like hallucinations and unreliable source verification persist despite incremental improvements.