AI RESEARCH
Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management
arXiv CS.LG
•
ArXi:2605.17036v1 Announce Type: cross This paper studies autonomous generative AI agents in multi-echelon supply chains using the MIT Beer Game. We identify four inference-time levers that shape performance: model selection, policies and guardrails, centralized data sharing, and prompt engineering. Model capability is the dominant factor: an out-of-the-box reasoning model exceeds human-level performance, and optimized reasoning models reduce costs by up to 67% relative to human teams. However, strong average performance masks substantial reliability risks. We