Metraipolis › archive › dc_bac57c5dfddf
SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis — arXiv:2609.03338
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03338
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:49:25.718Z
- SHA-256 of the archived text
0acfa90d3a6ab784fe67bccc33a7cda52ef3d7c697f45a712bb04cdaa856a45c- Stable URL of this page
https://metraipolis.com/documento/dc_bac57c5dfddf
How to cite
SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis — arXiv:2609.03338 — arXiv (en), https://arxiv.org/abs/2609.03338 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bac57c5dfddf (Metraipolis archive dc_bac57c5dfddf, sha256 0acfa90d3a6ab784fe67bccc33a7cda52ef3d7c697f45a712bb04cdaa856a45c)
BibTeX
@misc{dcbac57c5dfddf,
title = {SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis — arXiv:2609.03338},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03338},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bac57c5dfddf; sha256 0acfa90d3a6ab784fe67bccc33a7cda52ef3d7c697f45a712bb04cdaa856a45c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03338. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scientific literature synthesis agents increasingly rely on proprietary online services, limiting reproducibility, privacy, and offline deployment. To address this challenge, we introduce SciLENS Scientific Localized Evidence Navigation and Synthesis), a fully local autonomous agent framework operating on a dual-tier infrastructure indexing approximately 12 million academic records. SciLENS pioneers the integration of structural visualization as an actionable tool within the reasoning loop, enabling the agent to compress complex citation topologies into validated data-driven charts and thereby mitigate context exhaustion during macro-level synthesis. To train the agent without human annotation, we develop an automated data synthesis pipeline that extracts multi-hop subgraphs from a citation knowledge graph, verified by cross-model consensus among 20 frontier models. The agent is subsequently aligned through a reverse-decomposition rubric strategy that provides fine-grained process rewards for early planning and strict evidence grounding. Evaluations across six scientific benchmarks encompassing standard QA, citation accuracy, factual reasoning, and structural synthesis demonstrate that SciLENS significantly outperforms open-source baselines and achieves performance comparable to GPT-5.2 and Gemini-3.0-pro. Our source code and data are released at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.IR). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.03338 — 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 2026-10-17T02:27:00.296Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).