<?xml version="1.1" encoding="utf-8"?>
<article xsi:noNamespaceSchemaLocation="http://jats.nlm.nih.gov/publishing/1.1/xsd/JATS-journalpublishing1-mathml3.xsd" dtd-version="1.1" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><front><journal-meta><journal-id journal-id-type="publisher-id">PBES</journal-id><journal-title-group><journal-title>Proceedings of Business and Economic Studies</journal-title></journal-title-group><issn>2209-2641</issn><eissn>2209-265X</eissn><publisher><publisher-name>Bio-Byword Scientific Publishing Pty. Ltd.</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.26689/PBES.v9i10.16230</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title>Agentic AI-Driven Reverse Supply Chains for Electric Vehicle Batteries: Digital Battery Passports, Recovery Decisions, and Quantitative Experimental Validation</title><url>https://artdesignp.com/journal/PBES/9/10/10.26689/PBES.v9i10.16230</url><author>ZouShenfan</author><pub-date pub-type="publication-year"><year>2026</year></pub-date><volume>9</volume><issue>10</issue><history><date date-type="pub"><published-time>2026-11-19</published-time></date></history><abstract>End-of-use EV batteries pose a coordination problem: lifecycle data must become safe, timely recovery actions. This study tests a bounded agentic AI architecture in which the Digital Battery Passport (DBP) acts as shared evidence for recovery assessment, reverse logistics, material reintegration, and governance. Instead of survey evidence, we use a controlled Monte Carlo experiment: 30 matched replications, each with 1,000 generated battery-return cases, comparing human-coordinated planning, deterministic rule-based routing, and DBP-grounded agentic orchestration. Against the human baseline, agentic coordination cut mean decision-cycle time from 48.59 to 17.86 min (63.2%), lifted circular recovery yield from 81.86% to 83.55%, raised correct allocation from 79.65% to 92.70%, and reduced premature recycling from 9.44% to 4.71%. Static rules were faster in raw processing but weaker in routing quality and second-life capture. A 20-percentage-point drop in DBP completeness degraded key outcomes. These are computational results under stated assumptions, not observed industry estimates.</abstract><keywords>Agentic artificial intelligence, Electric vehicle battery, Reverse supply chain, Digital Battery Passport, Second life, Recycling, Quantitative validation</keywords></article-meta></front><body/><back><ref-list><ref id="B1" content-type="article"><label>1</label><element-citation publication-type="journal"><p>[1] Altuntas Vural C, van Loon P, Halld&amp;oacute;rsson &amp;Aacute;, et al., 2025, Life After Use: Circular Supply Chains for Second-Life of Electric Vehicle Batteries. Production Planning &amp;amp; Control, 36(9): 1229&amp;ndash;1246. https://doi.org/10.1080/09537287.2024.2353379.
[2] Xu M, Duong QH, Fernandez De Arroyabe Arranz C, Sun W, et al., 2026, Developing a Holistic Circular Business Model Framework for the EV Battery Closed-Loop Supply Chain: A data-driven approach. Technovation, 152: 103487. https://doi.org/10.1016/j.technovation.2026.103487.
[3] Berger K, Sch&amp;ouml;ggl J-P, Baumgartner RJ, 2022, Digital Battery Passports to Enable Circular and Sustainable Value Chains: Conceptualization and Use Cases. Journal of Cleaner Production, 353: 131492. https://doi.org/10.1016/j.jclepro.2022.131492.
[4] European Parliament and Council of the European Union, 2023, Regulation (EU) 2023/1542 of the European Parliament and of the Council of 12 July 2023 Concerning Batteries and Waste Batteries, Amending Directive 2008/98/EC and Regulation (EU) 2019/1020 and repealing Directive 2006/66/EC. Official Journal of the European Union, L 191: 1&amp;ndash;117.
[5] Losa R, Torjesen S, 2025, The Quest for More Circular Battery Value Chains: Implementing the EU Digital Battery Passport and Remaining Challenges. Cleaner Production Letters, 9: 100118. https://doi.org/10.1016/j.clpl.2025.100118.
[6] Pohlmann A, Popowicz M, Sch&amp;ouml;ggl J-P, et al., 2025, Digital Product Passports for Electric Vehicle Batteries: Stakeholder Requirements for Sustainability and Circularity. Cleaner Production Letters, 8: 100090. https://doi.org/10.1016/j.clpl.2024.100090.
[7] Aylak BL, 2025, SustAI-SCM: Intelligent Supply Chain Process Automation with Agentic AI for Sustainability and Cost Efficiency. Sustainability, 17(6): 2453. https://doi.org/10.3390/su17062453.
[8] Ivanov D, 2026, Agentic Digital Twins: Bridging Model-Based and AI-Driven Decision-Making Support for a New Era of Supply Chain and Operations Management. International Journal of Production Research, 64(15): 6574&amp;ndash;6590. https://doi.org/10.1080/00207543.2026.2630277.
[9] Jannelli V, Sch&amp;ouml;pf S, Bickel M, et al., 2025, Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seeking. International Journal of Production Research, 2025. https://doi.org/10.1080/00207543.2025.2604311.
[10] Korth M, Benfer M, Lanza G, 2026, Multi-Agentic Production Planning Utilising Simulation and Optimisation. CIRP Annals, 75(1): 595&amp;ndash;599. https://doi.org/10.1016/j.cirp.2026.04.027.
[11] Guzm&amp;aacute;n Ortiz E, Andres B, Torres-Polo M, 2026, A Cooperative Digital Twin&amp;ndash;Multi-Agent Reinforcement Learning for Circular Supply Chains: Balanced Control Across Production, Logistics, and Sustainability. Computers &amp;amp; Industrial Engineering, 218: 112044. https://doi.org/10.1016/j.cie.2026.112044.
[12] Statkiewicz W, Ragin-Skorecka K, Krzywy J, et al., 2026, Toward Circular Electromobility: Integrating Digital Product Passports into EV Battery Disassembly Processes. Procedia Computer Science, 277: 1704&amp;ndash;1713. https://doi.org/10.1016/j.procs.2026.02.208.
[13] Hassini M, Redondo-Iglesias E, Venet P, 2024, Battery Passports for Second-Life Batteries: An Experimental Assessment of Suitability for Mobile Applications. Batteries, 10(5): 153. https://doi.org/10.3390/batteries10050153
[14] Trifone N, Dallari F, Brintrup A, 2026, Drivers and Constraints of Agentic AI in Supply Chain Management: An Exploratory Study. International Journal of Production Research, 2026: 1&amp;ndash;40. https://doi.org/10.1080/00207543.2026.2669878.</p><pub-id pub-id-type="doi"/></element-citation></ref></ref-list></back></article>
