mlsanityData to 14 Oct 2026

Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management

arXiv 2605.17036 ↗First posted 16 May 2026cs.AI cs.LG cs.MAcited by 3

Not on the map. Why?

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.

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

15 of 50 references.

References · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  6. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  7. 2017Constrained Policy Optimizationcited by 983
  8. 2015Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approachcited by 170
  9. 2024InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chainscited by 22
  10. 2024Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seekingcited by 16
  11. 2025Large Language Models for Supply Chain Decisionscited by 13
  12. 2024Leveraging Graph Neural Networks and Multi-Agent Reinforcement Learning for Inventory Control in Supply Chainscited by 10
3 more
  1. 2023Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Riskcited by 9
  2. 2023On Implementing Autonomous Supply Chains: a Multi-Agent System Approachcited by 8
  3. 2022A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Banditscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactionscited by 5
  2. 2026When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight Marketscited by 1
  3. 2026Two-Timescale Hierarchical Reinforcement Learning for Resilient Operationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience
  2. 2026Agentic AI Autonomy Assessment: A Decision-Support Framework Towards Governed Supply Chain Systems
  3. 2026Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation
  4. 2026From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience
  5. 2024Generative Probabilistic Planning for Optimizing Supply Chain Networks
  6. 2025Iterative Multi-Agent Reinforcement Learning: A Novel Approach Toward Real-World Multi-Echelon Inventory Optimization
  7. 2025Closing the Loop: Coordinating Inventory and Recommendation via Deep Reinforcement Learning on Multiple Timescales
  8. 2026Automating Supply Chain Disruption Monitoring via an Agentic AI Approach