From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development
- URL: http://arxiv.org/abs/2609.11493v1
- Date: Thu, 10 Sep 2026 12:59:04 GMT
- Title: From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development
- Abstract summary: We present a modular agentic-AI platform that converts a heterogeneous corpus of process-development documents into a queryable, dual-layer knowledge graph.<n>We evaluate the lexical layer with a novel three-tier protocol measuring the deployment-fidelity of a retrieval-augmented generation (RAG) system on proprietary data.
- Score: 0.07646713951724012
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Chemistry, Manufacturing and Controls (CMC) process development generates an enormous body of technical information across a multi-stage, knowledge-intensive continuum from drug discovery to commercial manufacturing. This knowledge is traditionally fragmented across functions and heterogeneous formats, causing traceability gaps and significant knowledge-management costs during technology transfer and regulatory filing. We present a modular agentic-AI platform that converts a heterogeneous corpus of process-development documents into a queryable, dual-layer knowledge graph. A base knowledge layer builds a lexical graph with a Document-Section-Chunk hierarchy through lossless ingestion of digital, scanned, handwritten, and multilingual documents, while an intelligence layer extracts ontology-aligned entities and bridges cross-document concepts through a provenance-anchored domain graph. LLM agents operate across both layers, selecting the retrieval path best suited to each question. We evaluate the lexical layer with a novel three-tier protocol measuring the deployment-fidelity of a retrieval-augmented generation (RAG) system on proprietary data, demonstrated on 505 questions curated from 38 development reports of a Sanofi small-molecule program. Tier-1 multiple-choice accuracy of 95% signals strong platform reliability; the stricter Tier-2 LLM-judge pass rate of 85%, which degrades on comparative and corpus-wide questions, reveals a failure taxonomy that Tier-1 accuracy alone fails to capture. A router agent selects between layers according to question type. We anticipate this protocol will enable future designers of agentic platforms to assess their systems against nonpublic databases, and that graph-based architectures will see broader adoption in pharma as a means of transforming fragmented document repositories into structured process intelligence.
Related papers
- Automated Hardware Validation Test Plan Generation for Large Scale AI Datacenter Platforms Using a Generative AI Multi-Agents Architecture [4.668322408437681]
This paper presents a generative AI multi-agent architecture that automates the generation of structured hardware validation test plans.<n> evaluated on two production platforms against manual baselines, the framework achieves coverage expansions of 74.2% and 51.4%, cutting authoring from days to hours.
arXiv Detail & Related papers (2026-07-17T17:41:33Z) - The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems [3.7149543017244238]
This study empirically evaluates Retrieval-Augmented Generation (RAG) dependent architectures for the generation of files for GitHub repositories.<n>Results indicate a critical architectural trade-off: the Single-Agent pipeline achieves lexical quality comparable to MAS while reducing token consumption by 86% and operating at twice the speed.
arXiv Detail & Related papers (2026-06-29T16:29:31Z) - Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection [59.04089915447622]
ForenAgent is an interactive IFD framework that enables MLLMs to autonomously generate, execute, and refine Python-based low-level tools around the detection objective.<n>Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication.<n>Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks.
arXiv Detail & Related papers (2025-12-18T08:38:44Z) - Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions [8.97512410819274]
This paper presents the first empirical study on how state-of-the-art multi-agent systems perform in dataset adaptation tasks.<n>We evaluate GitHub Copilot on adapting SE research artifacts from benchmark repositories including ROCODE and LogHub2.0.<n>Results show that current systems can identify key files and generate partial adaptations but rarely produce correct implementations.
arXiv Detail & Related papers (2025-11-26T13:26:11Z) - URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding [55.45331924836242]
We present URaG, a framework that Unifies Retrieval and Generation within a single MLLM.<n>We show that URaG achieves state-of-the-art performance while reducing computational overhead by 44-56%.
arXiv Detail & Related papers (2025-11-13T17:54:09Z) - Executable Knowledge Graphs for Replicating AI Research [65.41207324831583]
Executable Knowledge Graphs (xKG) is a modular and pluggable knowledge base that automatically integrates technical insights, code snippets, and domain-specific knowledge extracted from scientific literature.<n>Code will released at https://github.com/zjunlp/xKG.
arXiv Detail & Related papers (2025-10-20T17:53:23Z) - A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System [56.40989626804489]
This survey provides the first holistic analysis of Large Language Models-powered software engineering.<n>We review over 150 recent papers and propose a taxonomy along two key dimensions: (1) Solutions, categorized into prompt-based, fine-tuning-based, and agent-based paradigms, and (2) Benchmarks, including tasks such as code generation, translation, and repair.
arXiv Detail & Related papers (2025-10-10T06:56:50Z) - MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection [84.75972919995398]
This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles.<n>The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent, and (iv) a web-scraped data analyzer.<n>Results demonstrate that the multi-agent ensemble achieves 95.3% accuracy with an F1 score of 0.964, significantly outperforming individual agents and traditional approaches.
arXiv Detail & Related papers (2025-08-13T19:14:48Z) - Deep Research Agents: A Systematic Examination And Roadmap [109.53237992384872]
Deep Research (DR) agents are designed to tackle complex, multi-turn informational research tasks.<n>In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute DR agents.
arXiv Detail & Related papers (2025-06-22T16:52:48Z) - HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation [11.53083922927901]
HM-RAG is a novel Hierarchical Multi-agent Multimodal RAG framework.<n>It pioneers collaborative intelligence for dynamic knowledge synthesis across structured, unstructured, and graph-based data.
arXiv Detail & Related papers (2025-04-13T06:55:33Z) - Reverse-Engineering the Retrieval Process in GenIR Models [41.661577386460436]
Generative Information Retrieval (GenIR) is a novel paradigm in which a transformer encoder-decoder model predicts document rankings based on a query.<n>This work studies the internal retrieval process of GenIR models by applying methods based on mechanistic interpretability.
arXiv Detail & Related papers (2025-03-25T14:41:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.