{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.26072", "kind": "paper", "url": "https://arxiv.org/abs/2607.26072"}], "authors": ["Changyu Du", "Alexander Vosseler", "Filippo Mazza", "André Borrmann"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.26072", "source_url": "https://arxiv.org/abs/2607.26072"}, "categories": ["General AI", "Information retrieval", "Language & Knowledge", "cs.IR"], "description": {"en": "IFCMemoryBench evaluates long-term memory in LLM-based agents for BIM information retrieval, with 143 multi-session tasks across 19 projects and 4,016 prior sessions, requiring integration of remembered context with live IFC queries."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.26072", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.26072", "title": "IFCMemoryBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Technical University of Munich", "Nemetschek (Germany)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.26072", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.26072", "source_url": "https://openalex.org/W7171862808"}, "key": "claire-radar:2607.26072", "modality": null, "name": "IFCMemoryBench", "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_ifcmemorybench_f2c4e9c3", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d67d7628311be68b7b5da7613517674288ca963326c5dfb036fe7f0999378289", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.26072"}, "publisher": null, "released": "2026-07-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.26072", "source_url": "https://arxiv.org/abs/2607.26072"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-26072", "source": "claire_radar", "source_benchmark_id": "2607.26072", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "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/2607.26072", "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": ["Information retrieval"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "130a6741595f56737952fc8d1620137b90d8b59ba67b1586753db1347b86e2a4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "IFCMemoryBench evaluates long-term memory in LLM-based agents for BIM information retrieval, with 143 multi-session tasks across 19 projects and 4,016 prior sessions, requiring integration of remembered context with live IFC queries.", "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 IFCMemoryBench, a benchmark for evaluating long-term memory in LLM-based BIM information retrieval."}, "familyId": "bmf_c1b4184d38fa", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_ifcmemorybench_f2c4e9c3", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.26072", "paper": "https://arxiv.org/abs/2607.26072", "pdf": "https://arxiv.org/pdf/2607.26072", "project": null, "report": "https://arxiv.org/abs/2607.26072"}, "metrics": [], "motivation": "Long-term memory is becoming a core capability of LLM-based agents, but existing evaluations largely test conversational recall in open-domain or persona-grounded settings.", "name": "IFCMemoryBench", "oneLine": "IFCMemoryBench evaluates long-term memory in LLM-based agents for BIM information retrieval, with 143 multi-session tasks across 19 projects and 4,016 prior sessions, requiring integration of remembered context with live IFC queries.", "paperTitle": "IFCMemoryBench: Evaluating Long-Term Memory of LLM-Based Agents in BIM Information Retrieval", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.26072", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.26072"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-13", "source": {"authors": ["Changyu Du", "Alexander Vosseler", "Filippo Mazza", "Andr\\'e Borrmann"], "categories": ["cs.IR", "cs.AI"], "id": "2607.26072", "title": "IFCMemoryBench: Evaluating Long-Term Memory of LLM-Based Agents in BIM Information Retrieval", "type": "arxiv", "url": "https://arxiv.org/abs/2607.26072"}, "sourceUpdatedAt": "2026-07-13T08:45:00Z", "topics": ["cs.IR"], "venueAttempts": [], "whyItMatters": "Existing memory evaluations focus on conversational recall, not professional domains. IFCMemoryBench provides a test for whether agents can reuse information across sessions in a structured, domain-specific environment, revealing gaps in current memory systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
