# Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management

arXiv: https://arxiv.org/abs/2605.17036 · HTML: https://mlsanity.com/paper/2605.17036/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 16 May 2026.

## Builds on (most cited first, 15 of 15)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach](https://mlsanity.com/paper/1506.02188/) (2015)
- [InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains](https://mlsanity.com/paper/2407.11384/) (2024)
- [Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seeking](https://mlsanity.com/paper/2411.10184/) (2024)
- [Large Language Models for Supply Chain Decisions](https://mlsanity.com/paper/2507.21502/) (2025)
- [Leveraging Graph Neural Networks and Multi-Agent Reinforcement Learning for Inventory Control in Supply Chains](https://mlsanity.com/paper/2410.18631/) (2024)
- [Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk](https://mlsanity.com/paper/2304.04341/) (2023)
- [On Implementing Autonomous Supply Chains: a Multi-Agent System Approach](https://mlsanity.com/paper/2310.09435/) (2023)
- [A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Bandits](https://mlsanity.com/paper/2206.02969/) (2022)

## Built on by (most cited first, 3 of 3)

- [Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions](https://mlsanity.com/paper/2606.02859/) (2026)
- [When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight Markets](https://mlsanity.com/paper/2607.19967/) (2026)
- [Two-Timescale Hierarchical Reinforcement Learning for Resilient Operations](https://mlsanity.com/paper/2607.23434/) (2026)

## Abstract (arXiv)

This paper studies the performance and reliability of autonomous generative AI agents in multi-echelon supply chains using the MIT Beer Game. We examine how model choice, operational guardrails, centralized data sharing, and prompt design affect system performance. In our best-performing configuration, GenAI agents reduce total supply-chain costs by up to 80% relative to human teams. Despite strong average performance, autonomous agents can exhibit substantial run-to-run instability, generating volatile procurement decisions and large tail costs. We characterize this phenomenon as agent bullwhip, the amplification of decision instability in autonomous multi-agent systems. We show that this instability can propagate across echelons and compound over time, even when the underlying demand path is held fixed. We then evaluate two approaches for improving reliability: reinforcement-learning post-training and operational guardrails. Both reduce tail events and mitigate agent bullwhip, but they operate through different mechanisms and require different levels of information and model access. Reinforcement-learning post-training delivers the largest gains in reliability and system performance when system-level feedback is available, while guardrails provide a simple training-free alternative for constraining extreme decisions.