← Back ◬ AI & Machine Learning Jun 10, 2026

ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience

arXiv AI Archived Jun 10, 2026 ✓ Full text saved

arXiv:2606.10359v1 Announce Type: new Abstract: AI agents in supply chains face a fundamental epistemic gap: large language models (LLMs) interpret policies but lack physical grounding, while reinforcement learning (RL) optimizes flows but is semantically blind to unstructured constraints. We introduce REFLECTICHAIN, bridging this gap through a Generative Supply Chain World Model (SC-WM) - encoding heterogeneous supply networks into a 6-dim graph-latent space with physical conservation - and Dou

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Artificial Intelligence [Submitted on 9 Jun 2026] ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience Jia Luo AI agents in supply chains face a fundamental epistemic gap: large language models (LLMs) interpret policies but lack physical grounding, while reinforcement learning (RL) optimizes flows but is semantically blind to unstructured constraints. We introduce REFLECTICHAIN, bridging this gap through a Generative Supply Chain World Model (SC-WM) - encoding heterogeneous supply networks into a 6-dim graph-latent space with physical conservation - and Double-Loop Learning that separates epistemic uncertainty (KL-trust-region-bounded policy adaptation) from aleatoric uncertainty (stochastic latent rollouts). On Semi-Sim, a 10-node semiconductor benchmark with SIR risk propagation, 6 perturbation types, and 10 policy constraint templates, REFLECTICHAIN improves Rationale Consistency Score by 33.0% (p < 0.0001, d = 2.78), maintains 82.3% operability under adversarial shocks, and exhibits anti-fragile behavior (+40.2% gain under moderate pressure). We identify three operational epistemic mechanisms - uncertainty separation, knowledge-boundary detection, and empirical Bayesian policy updating - and discuss five limitation categories. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.10359 [cs.AI] (or arXiv:2606.10359v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2606.10359 Focus to learn more Submission history From: Jia Luo [view email] [v1] Tue, 9 Jun 2026 03:18:44 UTC (2,116 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev | next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes