arXiv cs.AI· Gihan Panapitiya·· 12 小时前AI 评分38
Optimist Deep Research：面向自主文献研究的迭代式状态中心智能体
Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research
AI 导读
Optimist Deep Research 是一个开源智能体，把文献研究建模为围绕显式可变研究状态的迭代证据获取过程，将问题拆成子问题树并通过 arXiv、OpenAlex、Crossref、PubMed、Semantic Scholar 和网络检索。案例研究中它在约三分半钟内阅读了 237 篇检索文档中的 28 篇，最终报告逐节由证据库写成，每条引用都可解析到已检索文档。
正文 · 原文
Abstract:Most retrieval-augmented systems treat literature search as a single retrieval step followed by summarization. Real literature research works differently: the investigator's understanding of the question changes as they read, new subquestions appear, and evidence is weighed, not just collected. We present Optimist Deep Research, an open-source agent that runs literature research as an iterative evidence-acquisition process over an explicit, mutable research state. A research question is broken into a tree of subquestions, each served by search intents that are translated into source-specific queries over arXiv, OpenAlex, Crossref, PubMed, Semantic Scholar and the web. Results are merged into a canonical, provenance-preserving document registry through a conservative four-tier deduplication hierarchy. The registry is expanded by citation snowballing until a saturation criterion is met, and then screened, ranked and allocated to subquestions round-robin. Documents are read in parallel into a structured evidence store of claims with support, location, type and strength. A critic reviews the state along eight dimensions and returns research actions rather than a binary verdict: it can add, split, rephrase, deprioritize or close subquestions, so the research plan is an output of the investigation as well as an input. The final report is written section by section from the evidence store, and every citation resolves to a retrieved document. We describe the design, the deterministic machinery that keeps a language-model pipeline auditable, and a case study that read 28 of 237 retrieved documents in about three and a half minutes. We also report weaknesses the case study exposed.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.23299 [cs.AI] |
| (or arXiv:2610.23299v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23299 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gihan Panapitiya [view email]
[v1]
Fri, 16 Oct 2026 11:04:43 UTC (31 KB)
来源：arXiv cs.AI · arxiv.org