Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management

• URL: http://arxiv.org/abs/2605.17036v2
• Date: Thu, 21 May 2026 03:07:14 GMT
• Title: Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management
• Abstract summary: This paper studies autonomous generative AI agents in multi-echelon supply chains using the MIT Beer Game.<n>We identify four inference-time levers that shape performance: model selection, policies and guardrails, centralized data sharing, and prompt engineering.
• Score: 15.19525853427301
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 introduce agent bullwhip: the amplification of run-to-run decision instability in autonomous multi-echelon systems. A central component is decision bullwhip, the portion of order variability generated by stochastic agent decisions rather than by changes in customer demand. We show that decision instability can amplify both across facilities at a fixed point in time and within the same facility over time, even when the demand path is held fixed. Repeated sampling, a natural test-time remedy, fails to meaningfully reduce this instability, suggesting that reliability requires changing the underlying decision policy rather than merely averaging over model outputs. To address this limitation, we propose a Group Relative Policy Optimization (GRPO)-based reinforcement-learning post-training framework that trains a shared base LLM using system-level supply-chain rewards. Post-training substantially reduces tail events, curtails agent bullwhip, and improves the reliability of autonomous supply-chain agents.

Related papers

• Strategic Decision Support for AI Agents [26.38833436936642]
  In modern agentic systems, AI agents act on behalf of users, while humans and tools become support mechanisms around them.<n>This role reversal brings reliability concerns to the forefront, since agentic errors can be consequential.<n>We propose a framework for strategic decision support for AI agents through an optimization problem that minimizes support usage.
  arXiv  Detail & Related papers  (2026-06-10T18:34:36Z)
• Self-evolving LLM agents with in-distribution Optimization [60.05867547965365]
  Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments.<n>We propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning.<n>We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance.
  arXiv  Detail & Related papers  (2026-06-05T15:09:52Z)
• SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents [11.616028403813031]
  Large language models (LLMs) are increasingly deployed for autonomous financial trading.<n>We introduce the Self-Evolving Human-Auditable Policy (SHARP), a neuro-symbolic framework that replaces unconstrained text mutation with structured, symbolic policy optimization.
  arXiv  Detail & Related papers  (2026-05-07T18:23:44Z)
• AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents [37.232397795331444]
  We present AgentCollab, a self-driven collaborative inference framework that dynamically coordinates models with different reasoning capacities during agent execution.<n>Instead of relying on external routing modules, the framework uses the agent's own self-reflection signal to determine whether the current reasoning trajectory is making meaningful progress.
  arXiv  Detail & Related papers  (2026-03-27T03:07:34Z)
• Adaptive RAN Slicing Control via Reward-Free Self-Finetuning Agents [26.34195733862222]
  We propose a novel self-finetuning framework that enables agentic systems to learn continuously through direct interaction with the environment.<n>Our framework implements a bi-perspective reflection mechanism that generates autonomous linguistic feedback to construct preference datasets from interaction history.<n>A subsequent preference-based fine-tuning process distills long-horizon experiences into the model's parameters.<n> Experimental results show that our framework outperforms standard Reinforcement Learning (RL) baselines and existing Large Language Model (LLM)-based agents in sample efficiency, stability, and multi-metric optimization.
  arXiv  Detail & Related papers  (2026-03-11T09:14:56Z)
• Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems [17.658093330392052]
  We propose a game-theoretic framework that modifies inference-time decision making by interpolating between an agent's private objective and an estimate of group welfare.<n>We show that SWA induces a critical threshold $*=(n-)/(n-1)$ above which agents no longer have marginal incentive to increase demand under overload.
  arXiv  Detail & Related papers  (2026-02-16T05:17:58Z)
• AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection [14.17960333915609]
  Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability.<n>We introduce AdaptEvolve: Adaptive Selection for Multi-LLM Evolutionary Refinement.
  arXiv  Detail & Related papers  (2026-02-12T13:26:56Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Multi-Agent Conditional Diffusion Model with Mean Field Communication as Wireless Resource Allocation Planner [16.759740918605768]
  In wireless communication systems, efficient and adaptive resource allocation plays a crucial role in enhancing Quality of Service (QoS)<n>In contrast, the Distributed Training with Decentralized Execution (DTDE) paradigm enables distributed learning and decision-making.<n>We propose the Multi-Agent Conditional Diffusion Model Planner (MACDMP) for decentralized communication resource management.
  arXiv  Detail & Related papers  (2025-10-27T03:42:18Z)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards [80.78748457530718]
  Self-evolution is a central research topic in enabling large language model (LLM)-based agents to continually improve their capabilities after pretraining.<n>We introduce Co-Evolving Multi-Agent Systems (CoMAS), a novel framework that enables agents to improve autonomously by learning from inter-agent interactions.
  arXiv  Detail & Related papers  (2025-10-09T17:50:26Z)
• Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs [69.2486294522259]
  BaRP is a Bandit Routing-feedback with Preferences approach that trains under the same partial-feedback restriction as deployment.<n> Framed as a contextual bandit over prompt features and a user preference vector, our method simulates an online feedback setting during training and adapts its routing decisions to each new prompt.
  arXiv  Detail & Related papers  (2025-10-08T18:24:59Z)
• MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources [113.33902847941941]
  Variance-Aware Sampling (VAS) is a data selection strategy guided by Variance Promotion Score (VPS)<n>We release large-scale, carefully curated resources containing 1.6M long CoT cold-start data and 15k RL QA pairs.<n> Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS.
  arXiv  Detail & Related papers  (2025-09-25T14:58:29Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• Symbiotic Agents: A Novel Paradigm for Trustworthy AGI-driven Networks [1.5684305805304426]
  Large Language Model (LLM)-based autonomous agents are expected to play a vital role in the evolution of 6G networks.<n>We introduce a novel agentic paradigm that combines LLMs real-time optimization algorithms towards Trustworthy AI.<n>We propose an end-to-end architecture for AGI networks and evaluate it on a 5G testbed capturing channel fluctuations from moving vehicles.
  arXiv  Detail & Related papers  (2025-07-23T17:01:23Z)
• Efficient Beam Selection for ISAC in Cell-Free Massive MIMO via Digital Twin-Assisted Deep Reinforcement Learning [37.540612510652174]
  We derive the distribution of joint target detection probabilities across multiple receiving APs under false alarm rate constraints.<n>We then formulate the beam selection procedure as a Markov decision process (MDP)<n>To eliminate the high costs and associated risks of real-time agent-environment interactions, we propose a novel digital twin (DT)-assisted offline DRL approach.
  arXiv  Detail & Related papers  (2025-06-23T12:17:57Z)
• Self-Regulation and Requesting Interventions [63.5863047447313]
  We propose an offline framework that trains a "helper" policy to request interventions.<n>We score optimal intervention timing with PRMs and train the helper model on these labeled trajectories.<n>This offline approach significantly reduces costly intervention calls during training.
  arXiv  Detail & Related papers  (2025-02-07T00:06:17Z)
• Efficient Empowerment Estimation for Unsupervised Stabilization [75.32013242448151]
  empowerment principle enables unsupervised stabilization of dynamical systems at upright positions. We propose an alternative solution based on a trainable representation of a dynamical system as a Gaussian channel. We show that our method has a lower sample complexity, is more stable in training, possesses the essential properties of the empowerment function, and allows estimation of empowerment from images.
  arXiv  Detail & Related papers  (2020-07-14T21:10:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.