# Large Language Model Supply Chain: A Research Agenda

arXiv: https://arxiv.org/abs/2404.12736 · HTML: https://mlsanity.com/paper/2404.12736/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2024.

## Built on by (most cited first, 23 of 23)

- [Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents](https://mlsanity.com/paper/2503.15547/) (2025)
- [Position: Privacy Is Not Just Memorization!](https://mlsanity.com/paper/2510.01645/) (2025)
- [On the (In)Security of LLM App Stores](https://mlsanity.com/paper/2407.08422/) (2024)
- [A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework](https://mlsanity.com/paper/2604.23338/) (2026)
- [Large Language Model Supply Chain: Open Problems From the Security Perspective](https://mlsanity.com/paper/2411.01604/) (2024)
- [HuggingGraph: Understanding the Supply Chain of LLM Ecosystem](https://mlsanity.com/paper/2507.14240/) (2025)
- [SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime](https://mlsanity.com/paper/2602.19555/) (2026)
- [CRMAgent: A Multi-Agent LLM System for E-Commerce CRM Message Template Generation](https://mlsanity.com/paper/2507.08325/) (2025)
- [AgentReputation: A Decentralized Agentic AI Reputation Framework](https://mlsanity.com/paper/2605.00073/) (2026)
- [Where Agent Frameworks Fall Short: Examining Functional Challenges and Usability Concerns](https://mlsanity.com/paper/2602.21806/) (2026)
- [Learning to Generate Secure Code via Token-Level Rewards](https://mlsanity.com/paper/2602.23407/) (2026)
- [AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs](https://mlsanity.com/paper/2607.01640/) (2026)
- [Broken on Arrival: Silently Defective LLM Artifacts in Public Model Registries and How to Catch Them](https://mlsanity.com/paper/2609.05881/) (2026)
- [Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation](https://mlsanity.com/paper/2504.13551/) (2025)
- [NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models](https://mlsanity.com/paper/2508.11348/) (2025)
- [SAIL: SRAM-Accelerated LLM Inference System with Lookup-Table-based GEMV](https://mlsanity.com/paper/2509.25853/) (2025)
- [Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions](https://mlsanity.com/paper/2605.06279/) (2026)
- [LLMs for Enhanced Agricultural Meteorological Recommendations](https://mlsanity.com/paper/2408.04640/) (2024)
- [What Makes Code Generation Ethically Sourced?](https://mlsanity.com/paper/2507.19743/) (2025)
- [Rewriting the Response Path: Silent Tampering and Provider-Signed Defense in BYOK LLM Agents](https://mlsanity.com/paper/2605.02187/) (2026)
- [From Adoption to Deployment: A Qualitative Study on AI Integration in Software Development Practice](https://mlsanity.com/paper/2607.16660/) (2026)
- [A Security-Oriented Lifecycle Model for Large Language Model Systems](https://mlsanity.com/paper/2608.03626/) (2026)
- [On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models](https://mlsanity.com/paper/2608.10530/) (2026)

## Abstract (arXiv)

The rapid advancement of large language models (LLMs) has revolutionized artificial intelligence, introducing unprecedented capabilities in natural language processing and multimodal content generation. However, the increasing complexity and scale of these models have given rise to a multifaceted supply chain that presents unique challenges across infrastructure, foundation models, and downstream applications. This paper provides the first comprehensive research agenda of the LLM supply chain, offering a structured approach to identify critical challenges and opportunities through the dual lenses of software engineering (SE) and security & privacy (S&P). We begin by establishing a clear definition of the LLM supply chain, encompassing its components and dependencies. We then analyze each layer of the supply chain, presenting a vision for robust and secure LLM development, reviewing the current state of practices and technologies, and identifying key challenges and research opportunities. This work aims to bridge the existing research gap in systematically understanding the multifaceted issues within the LLM supply chain, offering valuable insights to guide future efforts in this rapidly evolving domain.