{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.15862", "kind": "paper", "url": "https://arxiv.org/abs/2606.15862"}], "authors": ["Linghua Zhang", "Jun Wang", "Jingtong Wu", "Zhisong Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.15862", "source_url": "https://arxiv.org/abs/2606.15862"}, "categories": ["Language & Knowledge", "Logistics & Operations", "Reasoning"], "description": {"en": "RetailBench is a simulation benchmark evaluating tool-using LLM agents in single-store supermarket operations over a 180-day horizon. It covers pricing, replenishment, supplier selection, assortment, inventory aging, customer feedback, external events, and cash-flow constraints, with a privileged oracle policy for comparison."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.15862", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.15862", "title": "RetailBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Ant Group (China)", "City University of Hong Kong"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.15862", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.15862", "source_url": "https://openalex.org/W7164921373"}, "key": "claire-radar:2606.15862", "modality": null, "name": "RetailBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_retailbench_1e87a5e2", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e161ae0cab7a784e52405dee6bc7bf55a705066e88c40e07acd509e2ae8b3aa4", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.15862"}, "publisher": null, "released": "2026-06-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.15862", "source_url": "https://arxiv.org/abs/2606.15862"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-15862", "source": "claire_radar", "source_benchmark_id": "2606.15862", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Logistics & Operations"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.15862", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "4cb9393ccb61d88fc5a48fcfeeac409e38663318a036a3fe9a0c2277a5b06b7d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RetailBench is a simulation benchmark evaluating tool-using LLM agents in single-store supermarket operations over a 180-day horizon. It covers pricing, replenishment, supplier selection, assortment, inventory aging, customer feedback, external events, and cash-flow constraints, with a privileged oracle policy for comparison.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce RetailBench, a data-grounded simulation benchmark for evaluating tool-using LLM agents in single-store supermarket operation."}, "familyId": "bmf_9a9797d125ac", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_retailbench_1e87a5e2", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Logistics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.15862", "paper": "https://arxiv.org/abs/2606.15862", "pdf": "https://arxiv.org/pdf/2606.15862", "project": null, "report": "https://arxiv.org/abs/2606.15862"}, "metrics": [], "motivation": "Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain.", "name": "RetailBench", "oneLine": "RetailBench is a simulation benchmark evaluating tool-using LLM agents in single-store supermarket operations over a 180-day horizon. It covers pricing, replenishment, supplier selection, assortment, inventory aging, customer feedback, external events, and cash-flow constraints, with a privileged oracle policy for comparison.", "paperTitle": "RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments", "primaryDomain": "Logistics & Operations", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.15862", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-14", "source": {"authors": ["Linghua Zhang", "Jun Wang", "Jingtong Wu", "and Zhisong Zhang"], "categories": ["cs.AI"], "id": "2606.15862", "title": "RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments", "type": "arxiv", "url": "https://arxiv.org/abs/2606.15862"}, "sourceUpdatedAt": "2026-06-19T10:48:19Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "RetailBench addresses the gap in evaluating LLM agents on long-horizon, economically grounded decision-making, where short-horizon tasks dominate existing benchmarks. It provides a controlled testbed for assessing coherent decision-making and reliability in dynamic environments."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
