{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.04667", "kind": "paper", "url": "https://arxiv.org/abs/2609.04667"}, {"id": "gh:gair-nlp/erp-bench", "kind": "repo", "url": "https://github.com/GAIR-NLP/erp-bench"}], "authors": ["Xinran Zhang", "Pengrui Lu", "Lyumanshan Ye", "Pengfei Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.04667", "source_url": "https://arxiv.org/abs/2609.04667"}, "categories": ["Finance", "Language & Knowledge", "Logistics & Operations", "Planning", "cs.AI"], "description": {"en": "ERPBench evaluates LLM agents in a six-round ERP simulation with pricing, production, procurement, inventory, finance, and shared-market competition. It includes 100 fixed problems tested in Solo (vs rule-based opponents) and Arena (six agents competing) ecologies, scoring based on firm valuation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.04667", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.04667", "title": "ERPBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shanghai Jiao Tong University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.04667", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.04667", "source_url": "https://openalex.org/W7211874846"}, "key": "claire-radar:2609.04667", "modality": null, "name": "ERPBench", "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_erpbench_cad5b1ca", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "9bb99f30b96e063ce7c50fd5837840f93b0fab31df08bd6818c3a5294739db47", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-08T00:56:29.478814Z", "source_url": "https://arxiv.org/abs/2609.04667"}, "publisher": null, "released": "2026-09-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.04667", "source_url": "https://arxiv.org/abs/2609.04667"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-04667", "source": "claire_radar", "source_benchmark_id": "2609.04667", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["Logistics & Operations", "Finance"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-07", "attemptedAt": "2026-09-07T01:28:43.988909Z", "githubRepo": "https://github.com/GAIR-NLP/erp-bench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.04667", "observedAt": "2026-09-07T01:28:43.988909Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-07T01:28:43.988909Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-07T01:28:43.988909Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Broad appeal of LLM agents for enterprise decision-making, with a competitive arena mode likely to attract interest from AI and business process research communities.", "score": 75}, "capabilities": ["Planning"], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-08T08:59:06.803818Z", "inputHash": "2d58c6c0503d80713edd8064ea9b2e48991bb65b172ca5eedb58729fe50f1a8e", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark provides code, fixed problems, and evaluation protocols, enabling other teams to run the same comparison.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-08T00:56:29.478814Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ERPBench evaluates LLM agents in a six-round ERP simulation with pricing, production, procurement, inventory, finance, and shared-market competition. It includes 100 fixed problems tested in Solo (vs rule-based opponents) and Arena (six agents competing) ecologies, scoring based on firm valuation.", "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 ERPBench, an execution-instrumented benchmark for enterprise decision agents in a six-round Enterprise Resource Planning (ERP) simulation with coupled pricing, production, procurement, inventory, finance, and shared-market competition."}, "familyId": "bmf_48cf960b7bf5", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_erpbench_cad5b1ca", "indexedAt": "2026-09-07T00:39:11.978130Z", "industrySectors": ["Logistics", "Financial Services"], "links": {"code": "https://github.com/GAIR-NLP/erp-bench", "data": null, "paper": "https://arxiv.org/abs/2609.04667", "pdf": "https://arxiv.org/pdf/2609.04667", "project": null, "report": "https://arxiv.org/abs/2609.04667"}, "metrics": [], "motivation": "Large language model (LLM) agents are increasingly proposed for enterprise workflows, yet existing evaluations rarely test whether business-decision conclusions transfer across competitive market ecologies.", "name": "ERPBench", "oneLine": "ERPBench evaluates LLM agents in a six-round ERP simulation with pricing, production, procurement, inventory, finance, and shared-market competition. It includes 100 fixed problems tested in Solo (vs rule-based opponents) and Arena (six agents competing) ecologies, scoring based on firm valuation.", "paperTitle": "ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies", "primaryDomain": "Logistics & Operations", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.04667", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T00:39:11.978130Z"}, "publications": [], "publishers": [{"name": "GAIR-NLP", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/GAIR-NLP/erp-bench"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 124, "score": 23}, "method": "attention-ranking-v13", "rank": 124, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 319, "score": 23}, "method": "attention-ranking-v13", "rank": 319, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-04", "source": {"authors": ["Xinran Zhang", "Pengrui Lu", "Lyumanshan Ye", "Pengfei Liu"], "categories": ["cs.AI"], "id": "2609.04667", "title": "ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies", "type": "arxiv", "url": "https://arxiv.org/abs/2609.04667"}, "sourceUpdatedAt": "2026-09-04T02:58:29Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "This benchmark addresses whether agent rankings transfer across competitive market contexts, a key concern for real-world deployment. It offers paired evaluation across ecologies and execution-intervention analysis, supporting model selection for enterprise tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
