Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.04956 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918190268809216 |
|---|---|
| author | Mahbub, Maria Lama, Vanessa Das, Sanjay Starks, Brian Polchek, Christopher Silvers, Saffell Deck, Lauren Balaprakash, Prasanna Ghosal, Tirthankar |
| author_facet | Mahbub, Maria Lama, Vanessa Das, Sanjay Starks, Brian Polchek, Christopher Silvers, Saffell Deck, Lauren Balaprakash, Prasanna Ghosal, Tirthankar |
| contents | High-Risk Property (HRP) classification is critical at U.S. Department of Energy (DOE) sites, where inventories include sensitive and often dual-use equipment. Compliance must track evolving rules designated by various export control policies to make transparent and auditable decisions. Traditional expert-only workflows are time-consuming, backlog-prone, and struggle to keep pace with shifting regulatory boundaries. We demo ORCHID, a modular agentic system for HRP classification that pairs retrieval-augmented generation (RAG) with human oversight to produce policy-based outputs that can be audited. Small cooperating agents, retrieval, description refiner, classifier, validator, and feedback logger, coordinate via agent-to-agent messaging and invoke tools through the Model Context Protocol (MCP) for model-agnostic on-premise operation. The interface follows an Item to Evidence to Decision loop with step-by-step reasoning, on-policy citations, and append-only audit bundles (run-cards, prompts, evidence). In preliminary tests on real HRP cases, ORCHID improves accuracy and traceability over a non-agentic baseline while deferring uncertain items to Subject Matter Experts (SMEs). The demonstration shows single item submission, grounded citations, SME feedback capture, and exportable audit artifacts, illustrating a practical path to trustworthy LLM assistance in sensitive DOE compliance workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04956 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ORCHID: Orchestrated Retrieval-Augmented Classification with Human-in-the-Loop Intelligent Decision-Making for High-Risk Property Mahbub, Maria Lama, Vanessa Das, Sanjay Starks, Brian Polchek, Christopher Silvers, Saffell Deck, Lauren Balaprakash, Prasanna Ghosal, Tirthankar Artificial Intelligence Computation and Language High-Risk Property (HRP) classification is critical at U.S. Department of Energy (DOE) sites, where inventories include sensitive and often dual-use equipment. Compliance must track evolving rules designated by various export control policies to make transparent and auditable decisions. Traditional expert-only workflows are time-consuming, backlog-prone, and struggle to keep pace with shifting regulatory boundaries. We demo ORCHID, a modular agentic system for HRP classification that pairs retrieval-augmented generation (RAG) with human oversight to produce policy-based outputs that can be audited. Small cooperating agents, retrieval, description refiner, classifier, validator, and feedback logger, coordinate via agent-to-agent messaging and invoke tools through the Model Context Protocol (MCP) for model-agnostic on-premise operation. The interface follows an Item to Evidence to Decision loop with step-by-step reasoning, on-policy citations, and append-only audit bundles (run-cards, prompts, evidence). In preliminary tests on real HRP cases, ORCHID improves accuracy and traceability over a non-agentic baseline while deferring uncertain items to Subject Matter Experts (SMEs). The demonstration shows single item submission, grounded citations, SME feedback capture, and exportable audit artifacts, illustrating a practical path to trustworthy LLM assistance in sensitive DOE compliance workflows. |
| title | ORCHID: Orchestrated Retrieval-Augmented Classification with Human-in-the-Loop Intelligent Decision-Making for High-Risk Property |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2511.04956 |