{"paper":{"title":"SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An SOP-free framework lets LLMs autonomously synthesize executable procedures for supply chain tool use and delivers the strongest consistent performance.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lang Cao, Shengyue Guan, Yihao Liu","submitted_at":"2026-02-07T03:49:25Z","abstract_excerpt":"Large language models (LLMs) have shown promise in complex reasoning and tool-based decision making, motivating their application to real-world supply chain management. However, supply chain workflows require reliable long-horizon, multi-step orchestration grounded in domain-specific procedures, which remains challenging for current models. To systematically evaluate LLM performance in this setting, we introduce SupChain-Bench, a unified real-world benchmark that assesses both supply chain domain knowledge and long-horizon tool-based orchestration grounded in standard operating procedures (SOP"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SupChain-ReAct, an SOP-free framework that autonomously synthesizes executable procedures for tool use, achieves the strongest and most consistent tool-calling performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the tasks and standard operating procedures in SupChain-Bench accurately represent real-world supply chain workflows and that performance gains from SupChain-ReAct will generalize beyond the specific models and scenarios tested.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SupChain-Bench reveals substantial gaps in LLM reliability for long-horizon supply chain orchestration, while the proposed SupChain-ReAct framework improves tool-calling by autonomously synthesizing procedures.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An SOP-free framework lets LLMs autonomously synthesize executable procedures for supply chain tool use and delivers the strongest consistent performance.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d1b44a6b88d31c59a5dfb144f0bff82c76a3e6e5440c0138f5524f9f6b3f8c49"},"source":{"id":"2602.07342","kind":"arxiv","version":2},"verdict":{"id":"ca4685e4-28ca-4376-a74f-9019257a588c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:46:48.786277Z","strongest_claim":"SupChain-ReAct, an SOP-free framework that autonomously synthesizes executable procedures for tool use, achieves the strongest and most consistent tool-calling performance.","one_line_summary":"SupChain-Bench reveals substantial gaps in LLM reliability for long-horizon supply chain orchestration, while the proposed SupChain-ReAct framework improves tool-calling by autonomously synthesizing procedures.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the tasks and standard operating procedures in SupChain-Bench accurately represent real-world supply chain workflows and that performance gains from SupChain-ReAct will generalize beyond the specific models and scenarios tested.","pith_extraction_headline":"An SOP-free framework lets LLMs autonomously synthesize executable procedures for supply chain tool use and delivers the strongest consistent performance."},"references":{"count":21,"sample":[{"doi":"","year":2024,"title":"Smart routing for sustainable supply chain net- works: An ai and knowledge graph driven approach. Applied Sciences, 15(14):8001. Elizabeth Fons, Rachneet Kaur, Soham Palande, Zhen Zeng, Tucker Balch, ","work_id":"9bb80603-0f99-4cf7-a321-48890f9836db","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","work_id":"4aff48d9-c46d-41d9-904b-52251e559596","ref_index":2,"cited_arxiv_id":"2503.21460","is_internal_anchor":true},{"doi":"","year":null,"title":"Identifier Extraction:The system first parses the user’s query to extract the primary trade_order_id","work_id":"387b9cb7-30c9-4c4d-bf40-efa410e3b2ce","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"An order may be split into multiple fulfillments","work_id":"f50b75f3-3350-4797-940f-f7a269c37a8d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Status Check:For each fulfillment_id iden- tified in the previous step, the system queries its real-time status","work_id":"5b2d833a-6d72-41fa-823c-caa82a1f9dcb","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":21,"snapshot_sha256":"f91a2040f821c20cba4d2e477d167512e1f1f3a0db466929ade5c0742b69753b","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1e466faa7fe7dcf62506c25e1f9c907ee62368e8f0650c45986e6920b5b7af44"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}