Metraipolis › archive › dc_fc9cd447a4f9
Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research — arXiv:2610.23299
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.23299
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:42:33.208Z
- SHA-256 of the archived text
92b624ef2b310c541251f91ace3e13546b6a4183547534248a00cc0abd36796b- Stable URL of this page
https://metraipolis.com/documento/dc_fc9cd447a4f9
How to cite
Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research — arXiv:2610.23299 — arXiv (en), https://arxiv.org/abs/2610.23299 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc9cd447a4f9 (Metraipolis archive dc_fc9cd447a4f9, sha256 92b624ef2b310c541251f91ace3e13546b6a4183547534248a00cc0abd36796b)
BibTeX
@misc{dcfc9cd447a4f9,
title = {Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research — arXiv:2610.23299},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.23299},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc9cd447a4f9; sha256 92b624ef2b310c541251f91ace3e13546b6a4183547534248a00cc0abd36796b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23299. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.23299 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:39:10.073Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).