From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience

TL;DR

This paper presents ReflectiChain, a novel framework integrating world models and reinforcement learning to enhance supply chain resilience against geopolitical disruptions, outperforming existing LLM-based planners.

Contribution

The introduction of a generative world model with reflection-in-action and retrospective RL for autonomous policy evolution in supply chain planning is a key innovation.

Findings

ReflectiChain achieves 250% higher rewards under extreme scenarios.

It restores Operability Ratio from 13.3% to over 88.5%.

Ablation studies confirm the importance of physical grounding and double-loop learning.

Abstract

Semiconductor supply chains face unprecedented resilience challenges amidst global geopolitical turbulence. Conventional Large Language Model (LLM) planners, when confronting such non-stationary "Policy Black Swan" events, frequently suffer from Decision Paralysis or a severe Grounding Gap due to the absence of physical environmental modeling. This paper introduces ReflectiChain, a cognitive agentic framework tailored for resilient macroeconomic supply chain planning. The core innovation lies in the integration of Latent Trajectory Rehearsal powered by a generative world model, which couples reflection-in-action (System 2 deliberation) with delayed reflection-on-action. Furthermore, we leverage a Retrospective Agentic RL mechanism to enable autonomous policy evolution during the deployment phase (test-time). Evaluations conducted on our high-fidelity benchmark, Semi-Sim, demonstrate that under extreme scenarios such as export bans and material shortages, ReflectiChain achieves a 250% improvement in average step rewards over the strongest LLM baselines. It successfully restores the Operability Ratio (OR) from a deficient 13.3% to over 88.5% while ensuring robust gradient convergence. Ablation studies further underscore that the synergy between physical grounding constraints and double-loop learning is fundamental to bridging the gap between semantic reasoning and physical reality for long-horizon strategic planning.