{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.09946", "kind": "paper", "url": "https://arxiv.org/abs/2608.09946"}], "authors": ["Yiyang Li", "Weixiang Sun", "Tianyi Ma", "Kaiwen Shi", "Zheyuan Zhang", "Yanfang Ye"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.09946", "source_url": "https://arxiv.org/abs/2608.09946"}, "categories": ["General AI", "Robotics & Embodied AI", "cs.HC"], "description": {"en": "HoosierHelp is an interactive benchmark for evaluating LLM agents in social service navigation. Agents interact with simulated users, issue structured resource-search calls, and select final resources from 3,971 Indiana public social service resources. The evaluation focuses on constraint grounding and handling non-ideal user interactions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.09946", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.09946", "title": "HoosierHelp"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Notre Dame"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.09946", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.09946", "source_url": "https://openalex.org/W7202257980"}, "key": "claire-radar:2608.09946", "modality": null, "name": "HoosierHelp", "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_hoosierhelp_ef4e5cac", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5a7499a1c957f7f9506df732d2347dbba4ca334e6610a0788ce8139fa1b1bd3e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.09946"}, "publisher": null, "released": "2026-07-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.09946", "source_url": "https://arxiv.org/abs/2608.09946"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-09946", "source": "claire_radar", "source_benchmark_id": "2608.09946", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Robotics & Embodied AI", "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/2608.09946", "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": "7dddef945121a3ef83d8243de18132073fdbbfc3feb16b02440cf1d0f465c4b6", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "HoosierHelp is an interactive benchmark for evaluating LLM agents in social service navigation. Agents interact with simulated users, issue structured resource-search calls, and select final resources from 3,971 Indiana public social service resources. The evaluation focuses on constraint grounding and handling non-ideal user interactions.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce HoosierHelp, an interactive benchmark grounded in 3,971 Indiana public social service resources."}, "familyId": "bmf_7c4d86f1a55e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_hoosierhelp_ef4e5cac", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.09946", "paper": "https://arxiv.org/abs/2608.09946", "pdf": "https://arxiv.org/pdf/2608.09946", "project": null, "report": "https://arxiv.org/abs/2608.09946"}, "metrics": [], "motivation": "Social service navigation requires connecting help-seeking individuals to resources that satisfy their needs and specific constraints.", "name": "HoosierHelp", "oneLine": "HoosierHelp is an interactive benchmark for evaluating LLM agents in social service navigation. Agents interact with simulated users, issue structured resource-search calls, and select final resources from 3,971 Indiana public social service resources. The evaluation focuses on constraint grounding and handling non-ideal user interactions.", "paperTitle": "HoosierHelp: Benchmarking LLM Agents for Social Service Navigation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.09946", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-03", "source": {"authors": ["Yiyang Li", "Weixiang Sun", "Tianyi Ma", "Kaiwen Shi", "Zheyuan Zhang", "Yanfang Ye"], "categories": ["cs.HC", "cs.AI"], "id": "2608.09946", "title": "HoosierHelp: Benchmarking LLM Agents for Social Service Navigation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.09946"}, "sourceUpdatedAt": "2026-07-03T00:39:26Z", "topics": ["cs.HC"], "venueAttempts": [], "whyItMatters": "Existing benchmarks do not capture the interaction complexity and constraint-grounding demands of social service navigation. HoosierHelp addresses this gap by simulating realistic user behaviors, providing a basis for assessing agent reliability in a high-stakes domain where incorrect resource recommendations can have serious consequences."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
