Metraipolis › archive › dc_d3b3cc7f65db

Orchestrating Specialized Agents for Trustworthy Enterprise RAG — arXiv:2601.18267

Source
arXiv
Original
https://arxiv.org/abs/2601.18267
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:45.036Z
SHA-256 of the archived text
a7bce5adb2e6d684449260532fe24adaae9ff9f66553acd65af73d3cebe62213
Stable URL of this page
https://metraipolis.com/documento/dc_d3b3cc7f65db

How to cite

Orchestrating Specialized Agents for Trustworthy Enterprise RAG — arXiv:2601.18267 — arXiv, https://arxiv.org/abs/2601.18267 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d3b3cc7f65db (Metraipolis archive dc_d3b3cc7f65db, sha256 a7bce5adb2e6d684449260532fe24adaae9ff9f66553acd65af73d3cebe62213)
BibTeX
@misc{dcd3b3cc7f65db,
  title = {Orchestrating Specialized Agents for Trustworthy Enterprise RAG — arXiv:2601.18267},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2601.18267},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d3b3cc7f65db; sha256 a7bce5adb2e6d684449260532fe24adaae9ff9f66553acd65af73d3cebe62213},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2601.18267. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict traceability, and recovery from underspecified prompts. One-pass retrieval-and-write pipelines frequently yield shallow summaries, inconsistent grounding, and weak mechanisms for completeness verification. We introduce ADORE (Adaptive Deep Orchestration for Research in Enterprise), an agentic framework that replaces linear retrieval with iterative, user-steered investigation coordinated by a central orchestrator and a set of specialized agents. ADORE's key insight is that a structured Memory Bank (a curated evidence store with explicit claim-evidence linkage and section-level admissible evidence) enables traceable report generation and systematic checks for evidence completeness. Our contributions are threefold: (1) Memory-locked synthesis - report generation is constrained to a structured Memory Bank (Claim-Evidence Graph) with section-level admissible evidence, enabling traceable claims and grounded citations; (2) Evidence-coverage-guided execution - a retrieval-reflection loop audits section-level evidence coverage to trigger targeted follow-up retrieval and terminates via an evidence-driven stopping criterion; (3) Section-packed long-context grounding - section-level packing, pruning, and citation-preserving compression make long-form synthesis feasible under context limits. Across our evaluation suite, ADORE ranks first on DeepResearch Bench (52.65) and achieves the highest head-to-head preference win rate on DeepConsult (77.2%) against commercial systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2601.18267 — 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 2026-10-06T05:24:05.717Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).