{"record": {"aliases": ["When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents"], "artifacts": [{"id": "arxiv:2609.03467", "kind": "paper", "url": "https://arxiv.org/abs/2609.03467"}], "authors": ["Wen-Yu Chang", "Yun-Nung Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.03467", "source_url": "https://arxiv.org/abs/2609.03467"}, "categories": ["General AI", "Information retrieval", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates conversational memory retrieval in long-horizon agents across four query styles using a dataset derived from LoCoMo."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.03467", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.03467", "title": "LOCOMO-CONV"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.03467", "modality": null, "name": "LOCOMO-CONV", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_when-users-don-t-ask-benchmarking-context-_4327f09f", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "85831b5d5855dd33089802bc2f7210dc73f3d02e5b4a7c8f1cf1be6aac3bc144", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-07T00:42:15.394147Z", "source_url": "https://arxiv.org/abs/2609.03467"}, "publisher": null, "released": "2026-09-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.03467", "source_url": "https://arxiv.org/abs/2609.03467"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-03467", "source": "claire_radar", "source_benchmark_id": "2609.03467", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents"], "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/2609.03467", "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"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The benchmark reframes memory evaluation for conversational agents, but the lack of explicit public artifacts limits expected adoption.", "score": 24}, "capabilities": ["Information retrieval"], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-07T00:42:15.394147Z", "inputHash": "1dab27721f262e570a29b6c7fe71cd21255091593648607fae10ca987ced6673", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce LOCOMO-CONV, a conversa- tional memory benchmark derived from Lo- CoMo with four query styles: dialog, implicit, counterfactual, and composed.", "canonicalNameSource": "abstract", "decisionReason": "The paper mentions releasing auxiliary annotations, but no direct link to data or code is provided to verify a reusable benchmark.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-07T00:42:15.394147Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates conversational memory retrieval in long-horizon agents across four query styles using a dataset derived from LoCoMo.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce LOCOMO-CONV, a conversa- tional memory benchmark derived from Lo- CoMo with four query styles: dialog, implicit, counterfactual, and composed."}, "familyId": "bmf_965578e620a6", "firstSeenAt": "2026-09-04", "heat": null, "id": "bm_when-users-don-t-ask-benchmarking-context-_4327f09f", "indexedAt": "2026-09-04T00:41:56.430646Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.03467", "pdf": "https://arxiv.org/pdf/2609.03467", "project": null, "report": "https://arxiv.org/abs/2609.03467"}, "metrics": [], "motivation": "Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems.", "name": "LOCOMO-CONV", "oneLine": "Evaluates conversational memory retrieval in long-horizon agents across four query styles using a dataset derived from LoCoMo.", "paperTitle": "When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.03467", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-04T00:41:56.430646Z"}, "publications": [], "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": 0.6, "relation": "introduces", "releasedAt": "2026-09-03", "source": {"authors": ["Wen-Yu Chang", "Yun-Nung Chen"], "categories": ["cs.CL", "cs.AI"], "id": "2609.03467", "title": "When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2609.03467"}, "sourceUpdatedAt": "2026-09-03T07:24:33Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Shifts memory evaluation from QA-style probing to in-situ conversational use, revealing gaps in retrieval and response quality."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
