{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.30730", "kind": "paper", "url": "https://arxiv.org/abs/2608.30730"}, {"id": "gh:qwenlm/e-commercebench", "kind": "repo", "url": "https://github.com/QwenLM/E-CommerceBench"}], "authors": ["Wei Fan", "Xinjie Shen", "Xudong Guo", "Jianhong Tu", "Yang Su", "Yinger Zhang", "Lianghao Deng", "Fengyu Wang", "Baohua Dong", "Yangqiu Song", "Dayiheng Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.30730", "source_url": "https://arxiv.org/abs/2608.30730"}, "categories": ["Agents & Tool Use", "Logistics & Operations", "cs.LG"], "description": {"en": "Evaluates LLM agents over a deterministic 365-day simulated e-commerce operation, scoring asset growth, negotiation, fraud avoidance, efficiency, and learning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.30730", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.30730", "title": "E-Commerce Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.30730", "modality": null, "name": "E-Commerce Bench", "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": "true", "origin_record_id": "bm_e-commerce-bench_400b2b29", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0091f5df48bb95bc95f8af8034c89d98faf9bfb5138679bd6348eefc290e5d25", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.30730"}, "publisher": null, "released": "2026-08-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.30730", "source_url": "https://arxiv.org/abs/2608.30730"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-30730", "source": "claire_radar", "source_benchmark_id": "2608.30730", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Logistics & Operations"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": "https://github.com/QwenLM/E-CommerceBench", "githubScope": "benchmark_repo", "githubStars": 5, "hfDailySubmittedAt": "2026-09-02T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 3, "hfPaperUrl": "https://huggingface.co/papers/2608.30730", "observedAt": "2026-09-02T05:12:51.621571Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The open-source long-horizon agent benchmark with public code and broad model evaluation is likely to attract significant interest from the agent community.", "score": 70}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "a80a8b1a4f83a4eafb3154dd6ecc992f27c5d704322834a7f1f21987c3bd34a8", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark is open-source with available code, defines a clear scoring contract and leaderboard, and supports model submission comparison.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLM agents over a deterministic 365-day simulated e-commerce operation, scoring asset growth, negotiation, fraud avoidance, efficiency, and learning.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce E-Commerce Bench, the first open-source benchmark that integrates multi-round counterpart negotiation and dynamic events into a year-long business operation."}, "familyId": "bmf_c4bff3880a08", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_e-commerce-bench_400b2b29", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": ["Logistics"], "links": {"code": "https://github.com/QwenLM/E-CommerceBench", "data": null, "paper": "https://arxiv.org/abs/2608.30730", "pdf": "https://arxiv.org/pdf/2608.30730", "project": null, "report": "https://arxiv.org/abs/2608.30730"}, "metrics": [], "motivation": "Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns.", "name": "E-Commerce Bench", "oneLine": "Evaluates LLM agents over a deterministic 365-day simulated e-commerce operation, scoring asset growth, negotiation, fraud avoidance, efficiency, and learning.", "paperTitle": "E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation", "primaryDomain": "Logistics & Operations", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.30730", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "publications": [], "publishers": [{"name": "QwenLM", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/QwenLM/E-CommerceBench"}], "ranking": {"30d": {"confidence": "High", "coverage": 0.85, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.2668623713452529, "value": 5}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.2457137885628774, "value": 3}}, "confidence": "High", "coverage": 0.85, "rank": 91, "score": 30}, "method": "attention-ranking-v13", "rank": 91, "score": 30}, "90d": {"confidence": "Medium", "coverage": 0.7, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.2438663920360867, "value": 5}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.2457137885628774, "value": 3}}, "confidence": "Medium", "coverage": 0.7, "rank": 224, "score": 32}, "method": "attention-ranking-v13", "rank": 224, "score": 32}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-31", "source": {"authors": ["Wei Fan", "Xinjie Shen", "Xudong Guo", "Jianhong Tu", "Yang Su", "Yinger Zhang", "Lianghao Deng", "Fengyu Wang", "Baohua Dong", "Yangqiu Song", "Dayiheng Liu"], "categories": ["cs.LG", "cs.CL"], "id": "2608.30730", "title": "E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.30730"}, "sourceUpdatedAt": "2026-08-31T13:03:57Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Provides a reproducible long-horizon business environment with multi-dimensional metrics, exposing tradeoffs beyond final profit."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
