{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.14571", "kind": "paper", "url": "https://arxiv.org/abs/2606.14571"}, {"id": "gh:landian60/streammembench", "kind": "repo", "url": "https://github.com/landian60/StreamMemBench"}], "authors": ["Guanming Liu", "Yuqi Ren", "Hansu Gu", "Peng Zhang", "Weihang Wang", "Jiahao Liu", "Ning Gu", "Tun Lu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.14571", "source_url": "https://arxiv.org/abs/2606.14571"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "StreamMemBench is a streaming benchmark for evaluating agent memory with two-step task sequences around evidence anchors from EgoLife egocentric streams, with four diagnostic metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.14571", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.14571", "title": "StreamMemBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.14571", "modality": null, "name": "StreamMemBench", "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_streammembench_6345b534", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "4e0829ac12e8468be424c2f0eda41ab14a16905c49d69ebece554bb63aa31063", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.14571"}, "publisher": null, "released": "2026-06-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.14571", "source_url": "https://arxiv.org/abs/2606.14571"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-14571", "source": "claire_radar", "source_benchmark_id": "2606.14571", "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": "https://github.com/landian60/StreamMemBench", "githubScope": "benchmark_repo", "githubStars": 23, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.14571", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "status": "fresh"}, "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": "1e9604ff519227981ed24535395a4b69998f542eff33a3c1122d816caba19716", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "StreamMemBench is a streaming benchmark for evaluating agent memory with two-step task sequences around evidence anchors from EgoLife egocentric streams, with four diagnostic metrics.", "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", "public artifact URL"], "snippet": "We introduce StreamMemBench, a streaming benchmark that constructs a two-step task sequence around each evidence anchor from EgoLife egocentric streams."}, "familyId": "bmf_9ab5cd1646d9", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/landian60/StreamMemBench", "url": "https://github.com/landian60/StreamMemBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/landian60/StreamMemBench", "url": "https://huggingface.co/papers/2606.14571"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/landian60/StreamMemBench.", "url": "https://arxiv.org/abs/2606.14571"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/landian60/StreamMemBench", "url": "https://arxiv.org/abs/2606.14571"}], "scope": "benchmark_repo", "url": "https://github.com/landian60/StreamMemBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_streammembench_6345b534", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/landian60/StreamMemBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.14571", "paper": "https://arxiv.org/abs/2606.14571", "pdf": "https://arxiv.org/pdf/2606.14571", "project": null, "report": "https://arxiv.org/abs/2606.14571"}, "metrics": [], "motivation": "A central role of personal-agent memory is to turn stored information and prior interactions into future-oriented assistance.", "name": "StreamMemBench", "oneLine": "StreamMemBench is a streaming benchmark for evaluating agent memory with two-step task sequences around evidence anchors from EgoLife egocentric streams, with four diagnostic metrics.", "paperTitle": "StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to Findings of EMNLP 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.14571", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Findings of EMNLP 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-12", "source": {"authors": ["Guanming Liu", "Yuqi Ren", "Hansu Gu", "Peng Zhang", "Weihang Wang", "Jiahao Liu", "Ning Gu", "and Tun Lu"], "categories": ["cs.AI"], "id": "2606.14571", "title": "StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance", "type": "arxiv", "url": "https://arxiv.org/abs/2606.14571"}, "sourceUpdatedAt": "2026-06-12T15:48:43Z", "topics": ["Agents"], "venueAttempts": [{"decisionRaw": "Accepted to Findings of EMNLP 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to Findings of EMNLP 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.14571"}], "reviewStatus": "accepted", "venueName": "Findings of EMNLP 2026"}], "whyItMatters": "Existing memory benchmarks test recall or task improvement in isolation. StreamMemBench evaluates the trajectory from streaming observations to future-oriented assistance, diagnosing whether memory systems use evidence and incorporate feedback."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
