{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZWDREX3OKTCODS7LHJHCN6SCJ3","short_pith_number":"pith:ZWDREX3O","schema_version":"1.0","canonical_sha256":"cd87125f6e54c4e1cbeb3a4e26fa424ec408c40096bf3bd2486d3afcba3cf7fd","source":{"kind":"arxiv","id":"2605.17036","version":1},"attestation_state":"computed","paper":{"title":"Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Autonomous AI agents with optimized reasoning models outperform human teams in supply chain management by reducing costs up to 67 percent, but require post-training to control decision unreliability.","cross_cats":["cs.LG","cs.MA","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Andre P. Calmon, Carol Xuan Long, David Simchi-Levi, Feng Zhu, Flavio P. Calmon, Huangyuan Su","submitted_at":"2026-05-16T15:11:35Z","abstract_excerpt":"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 the agent bullwhip effect, the amplification of decision unrel"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.17036","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T15:11:35Z","cross_cats_sorted":["cs.LG","cs.MA","cs.SY","eess.SY"],"title_canon_sha256":"1eb7a4f4d7f8c595979ef1accca31a12fea55af2dce6d104b8957465a2b09f9a","abstract_canon_sha256":"6f28bfdd88d2fc0f3a3dee7e4b6715b21c75c6554a7758d40bb370656070c6be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:37.102116Z","signature_b64":"JibAOdWObkQBxMETflsXIoRjx950bHm4/u4llmcn4PpXzVjpFGFx9570X7OgPgCzpZoua9dJgik3XEjGFb4tCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd87125f6e54c4e1cbeb3a4e26fa424ec408c40096bf3bd2486d3afcba3cf7fd","last_reissued_at":"2026-05-20T00:03:37.101429Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:37.101429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Autonomous AI agents with optimized reasoning models outperform human teams in supply chain management by reducing costs up to 67 percent, but require post-training to control decision unreliability.","cross_cats":["cs.LG","cs.MA","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Andre P. Calmon, Carol Xuan Long, David Simchi-Levi, Feng Zhu, Flavio P. Calmon, Huangyuan Su","submitted_at":"2026-05-16T15:11:35Z","abstract_excerpt":"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 the agent bullwhip effect, the amplification of decision unrel"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"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. GRPO post-training substantially reduces tail events, curtails agent bullwhip, and improves the reliability of autonomous supply-chain agents.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The MIT Beer Game simulation with its ordering rules and information delays sufficiently captures the coordination dynamics of real multi-echelon supply chains (the entire experimental and theoretical framework is constructed on this testbed).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Autonomous AI agents outperform humans in supply chain simulations but exhibit an inherent agent bullwhip effect of amplified decision unreliability, mitigated by GRPO reinforcement learning post-training.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Autonomous AI agents with optimized reasoning models outperform human teams in supply chain management by reducing costs up to 67 percent, but require post-training to control decision unreliability.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d42ede4a3fbdc781deb3268be42be4ab6b4f5e795789a128a31eea46c23110b4"},"source":{"id":"2605.17036","kind":"arxiv","version":1},"verdict":{"id":"16948f34-9179-43f3-bd71-b961b42af81c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:09:12.106368Z","strongest_claim":"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. GRPO post-training substantially reduces tail events, curtails agent bullwhip, and improves the reliability of autonomous supply-chain agents.","one_line_summary":"Autonomous AI agents outperform humans in supply chain simulations but exhibit an inherent agent bullwhip effect of amplified decision unreliability, mitigated by GRPO reinforcement learning post-training.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The MIT Beer Game simulation with its ordering rules and information delays sufficiently captures the coordination dynamics of real multi-echelon supply chains (the entire experimental and theoretical framework is constructed on this testbed).","pith_extraction_headline":"Autonomous AI agents with optimized reasoning models outperform human teams in supply chain management by reducing costs up to 67 percent, but require post-training to control decision unreliability."},"integrity":{"clean":false,"summary":{"advisory":1,"critical":0,"by_detector":{"doi_compliance":{"total":1,"advisory":1,"critical":0,"informational":0}},"informational":0},"endpoint":"/pith/2605.17036/integrity.json","findings":[{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1080/24725854.2023.2217248.Niki) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":7,"audited_at":"2026-05-19T20:20:45.983094Z","detected_doi":"10.1080/24725854.2023.2217248.Niki","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T20:31:18.944638Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:20:45.983094Z","status":"completed","version":"1.0.0","findings_count":1},{"name":"citation_quote_validity","ran_at":"2026-05-19T19:49:42.513061Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T18:51:56.618092Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.167281Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:23.003121Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"65d34662547aec51f79cacf44c54a0e7be83bedab9899589be08edd501c0ea95"},"references":{"count":18,"sample":[{"doi":"10.1287/opre.1050.0238","year":null,"title":"Leonard Boussioux, Andrew Chen, Ming Fan, and Apurva Jain","work_id":"a4216f2f-82cb-4c8b-a9e0-5d3d2a3ab49f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","work_id":"b124064d-5a56-42ad-86f5-3cc349b86a3a","ref_index":2,"cited_arxiv_id":"2407.21787","is_internal_anchor":true},{"doi":"10.1023/a:1008195614074","year":null,"title":"Guillermo Gallego and Ilkyeong Moon","work_id":"fc272828-a718-469d-b2d1-3680f2d0c570","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1057/jors.1993.141","year":1993,"title":"Javier García and Fernando Fernández","work_id":"07253e14-faec-4b44-8a93-06fa7e6ae69b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1038/s41586-025-09422-z","year":null,"title":"Nature645(8081), 633–638 (2025) https://doi.org/10.1038/s41586-025-09422-z","work_id":"9835b482-5032-4135-93dd-82a066677569","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"8bb015b5f488f3e1ef6399198ba749f4208f0afd0d7c6ac730f7fc52bbda782f","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"89005928ddb4780468bdef62de7f289bfc1a6c229f0068ffea4b63eaafa79bf1"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.17036","created_at":"2026-05-20T00:03:37.101534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17036v1","created_at":"2026-05-20T00:03:37.101534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17036","created_at":"2026-05-20T00:03:37.101534+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWDREX3OKTCO","created_at":"2026-05-20T00:03:37.101534+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWDREX3OKTCODS7L","created_at":"2026-05-20T00:03:37.101534+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWDREX3O","created_at":"2026-05-20T00:03:37.101534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWDREX3OKTCODS7LHJHCN6SCJ3","json":"https://pith.science/pith/ZWDREX3OKTCODS7LHJHCN6SCJ3.json","graph_json":"https://pith.science/api/pith-number/ZWDREX3OKTCODS7LHJHCN6SCJ3/graph.json","events_json":"https://pith.science/api/pith-number/ZWDREX3OKTCODS7LHJHCN6SCJ3/events.json","paper":"https://pith.science/paper/ZWDREX3O"},"agent_actions":{"view_html":"https://pith.science/pith/ZWDREX3OKTCODS7LHJHCN6SCJ3","download_json":"https://pith.science/pith/ZWDREX3OKTCODS7LHJHCN6SCJ3.json","view_paper":"https://pith.science/paper/ZWDREX3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17036&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWDREX3OKTCODS7LHJHCN6SCJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWDREX3OKTCODS7LHJHCN6SCJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWDREX3OKTCODS7LHJHCN6SCJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWDREX3OKTCODS7LHJHCN6SCJ3/action/storage_attestation","attest_author":"https://pith.science/pith/ZWDREX3OKTCODS7LHJHCN6SCJ3/action/author_attestation","sign_citation":"https://pith.science/pith/ZWDREX3OKTCODS7LHJHCN6SCJ3/action/citation_signature","submit_replication":"https://pith.science/pith/ZWDREX3OKTCODS7LHJHCN6SCJ3/action/replication_record"}},"created_at":"2026-05-20T00:03:37.101534+00:00","updated_at":"2026-05-20T00:03:37.101534+00:00"}