{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.12385", "kind": "paper", "url": "https://arxiv.org/abs/2607.12385"}], "authors": ["Genglin Liu", "Saadia Gabriel"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.12385", "source_url": "https://arxiv.org/abs/2607.12385"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "PM-Bench evaluates prospective memory in LLM agents through a text-based simulated seven-day week. Agents must maintain user intentions, execute delayed intentions, and monitor latent environment changes while performing ongoing activities."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.12385", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.12385", "title": "PM-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of California, Los Angeles"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.12385", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.12385", "source_url": "https://openalex.org/W7168413016"}, "key": "claire-radar:2607.12385", "modality": null, "name": "PM-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": "unknown", "origin_record_id": "bm_pm-bench_3de97f77", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3b23e2b7cb981ff05dc6f9d159f295ead1a1c1d063bda2b942e2d466f6fd8c82", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.12385"}, "publisher": null, "released": "2026-07-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.12385", "source_url": "https://arxiv.org/abs/2607.12385"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-12385", "source": "claire_radar", "source_benchmark_id": "2607.12385", "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/2607.12385", "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": [], "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": "57ee1bd17b05250289c0cbe599796abada7eb96ca182b1109ed88ec2a995a9e2", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PM-Bench evaluates prospective memory in LLM agents through a text-based simulated seven-day week. Agents must maintain user intentions, execute delayed intentions, and monitor latent environment changes while performing ongoing activities.", "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 PM-Bench, a text-based benchmark for measuring prospective memory capabilities in modern LLM agents."}, "familyId": "bmf_ecbb460ae2fa", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_pm-bench_3de97f77", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.12385", "paper": "https://arxiv.org/abs/2607.12385", "pdf": "https://arxiv.org/pdf/2607.12385", "project": null, "report": "https://arxiv.org/abs/2607.12385"}, "metrics": [], "motivation": "A significant challenge in agentic AI is prospective memory: the ability to execute an intention at a specific future cue or state while other activities are ongoing.", "name": "PM-Bench", "oneLine": "PM-Bench evaluates prospective memory in LLM agents through a text-based simulated seven-day week. Agents must maintain user intentions, execute delayed intentions, and monitor latent environment changes while performing ongoing activities.", "paperTitle": "PM-Bench: Evaluating Prospective Memory in LLM Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.12385", "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/2607.12385"}], "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": "2026-07-14", "source": {"authors": ["Genglin Liu", "Saadia Gabriel"], "categories": ["cs.AI"], "id": "2607.12385", "title": "PM-Bench: Evaluating Prospective Memory in LLM Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2607.12385"}, "sourceUpdatedAt": "2026-07-14T05:57:32Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "PM-Bench fills a gap in evaluating agentic AI by measuring an understudied cognitive capability—prospective memory—in a controlled, repeatable setting. It provides a diagnostic tool for comparing LLM agents and guiding interventions to improve reliability in real-world tasks requiring memory for future actions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
