Metraipolis › archive › dc_2ee2cdbde6f8
TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives — arXiv:2609.19897
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19897
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:20:48.801Z
- SHA-256 of the archived text
82d97e703c2cbc1b52b11795f26d4257064c8d931866ac03193e1a8c016b08d5- Stable URL of this page
https://metraipolis.com/documento/dc_2ee2cdbde6f8
How to cite
TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives — arXiv:2609.19897 — arXiv (en), https://arxiv.org/abs/2609.19897 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ee2cdbde6f8 (Metraipolis archive dc_2ee2cdbde6f8, sha256 82d97e703c2cbc1b52b11795f26d4257064c8d931866ac03193e1a8c016b08d5)
BibTeX
@misc{dc2ee2cdbde6f8,
title = {TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives — arXiv:2609.19897},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19897},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ee2cdbde6f8; sha256 82d97e703c2cbc1b52b11795f26d4257064c8d931866ac03193e1a8c016b08d5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19897. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Historical archives pose a difficult retrieval problem for retrievalaugmented generation systems: documents are OCR-degraded, heterogeneous across genres and sources, and require strong source traceability for scholarly and institutional use. We introduce TRACE, a training-free agentic retrieval framework designed for accountable source discovery over historical corpora. The system was developed in the context of DECIDON, an interdisciplinary project on the circulation of political discourse between parliamentary debates and the press during the French Third Republic, involving digitised historical collections and institutional use cases. The prototype is currently deployed internally within the project and accessible to 24 researchers across six partner institutions. We evaluate TRACE on HistoriQA-ThirdRepublic, a benchmark of 1,752 French historical questions over parliamentary debates and newspapers from 1887, with documents derived from Biblioth{è}que nationale de France digitised collections. TRACE achieves R@10 = 0.856 and MRR = 0.653, outperforming sparse, dense, graph-based, and agentic RAG baselines, with the largest gains on multi-hop and cross-corpus questions. At approximately $0.02 per question under the default hosted inference configuration, TRACE also remains economically feasible for heritage institutions, laboratories or companies that cannot rely on costly local GPU infrastructure. These results suggest that, for large digital libraries and archives, retrieval accountability and corpus-aware agent design can provide a practical alternative to heavier training-based or graph-construction approaches.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.19897 — 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 2026-10-10T03:04:13.664Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).