{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.27453", "kind": "paper", "url": "https://arxiv.org/abs/2607.27453"}, {"id": "gh:veris-ai/riley-agent", "kind": "repo", "url": "https://github.com/veris-ai/riley-agent"}], "authors": ["Joshua Meyer", "Sahar Shayegan", "Ritiz Tambi", "Ali Khan", "Sun Kim", "Victor Shih", "Mehdi Jamei", "Andi Partovi"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.27453", "source_url": "https://arxiv.org/abs/2607.27453"}, "categories": ["Agents", "General AI", "Speech & Audio"], "description": {"en": "VAmoS Bench evaluates complete voice-agent systems in a stateful customer-support task, with 100 scenarios, a simulated caller, real SQL tools, and binary assertions assessed against full interaction traces."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.27453", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.27453", "title": "VAmoS Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.27453", "modality": null, "name": "VAmoS 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_vamos-bench_83d46046", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "762162b3b3b57e473892047305a20060245a4ce9e84f620108873caf089d65d6", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.27453"}, "publisher": null, "released": "2026-07-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.27453", "source_url": "https://arxiv.org/abs/2607.27453"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-27453", "source": "claire_radar", "source_benchmark_id": "2607.27453", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Speech & Audio", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/veris-ai/riley-agent", "githubScope": "benchmark_repo", "githubStars": 18, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.27453", "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", "state": "unavailable"}}, "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": "7f0d7e4077e7b8b6c367032c3d08c46f652f9b532fc516ef18eeac0ab9c02205", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "VAmoS Bench evaluates complete voice-agent systems in a stateful customer-support task, with 100 scenarios, a simulated caller, real SQL tools, and binary assertions assessed against full interaction traces.", "domainCuration": {"method": "primary-source-review-v1", "state": "reviewed"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce VAmoS Bench, the Voice Agent Simulation Bench."}, "familyId": "bmf_e925739160ae", "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/veris-ai/riley-agent", "url": "https://github.com/veris-ai/riley-agent"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/veris-ai/riley-agent", "url": "https://huggingface.co/papers/2607.27453"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/veris-ai/riley-agent", "url": "https://arxiv.org/abs/2607.27453"}], "scope": "project_repo", "url": "https://github.com/veris-ai/riley-agent", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_vamos-bench_83d46046", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/veris-ai/riley-agent", "data": null, "hfPaper": "https://huggingface.co/papers/2607.27453", "paper": "https://arxiv.org/abs/2607.27453", "pdf": "https://arxiv.org/pdf/2607.27453", "project": null, "report": "https://arxiv.org/abs/2607.27453"}, "metrics": [], "motivation": "Production voice agents span cascaded, speech-to-speech, and hybrid architectures.", "name": "VAmoS Bench", "oneLine": "VAmoS Bench evaluates complete voice-agent systems in a stateful customer-support task, with 100 scenarios, a simulated caller, real SQL tools, and binary assertions assessed against full interaction traces.", "paperTitle": "VAmoS Bench: Voice Agent Simulation Bench", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.27453", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Veris AI", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/veris-ai/riley-agent"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.3930296741270534, "value": 18}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 114, "score": 44}, "method": "attention-ranking-v13", "rank": 114, "score": 44}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-29", "source": {"authors": ["Joshua Meyer", "Sahar Shayegan", "Ritiz Tambi", "Ali Khan", "Sun Kim", "Victor Shih", "Mehdi Jamei", "Andi Partovi"], "categories": ["cs.AI"], "id": "2607.27453", "title": "VAmoS Bench: Voice Agent Simulation Bench", "type": "arxiv", "url": "https://arxiv.org/abs/2607.27453"}, "sourceUpdatedAt": "2026-07-29T20:42:38Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "It measures end-to-end call containment and correct backend mutations, going beyond component metrics to capture task-level correctness in realistic scenarios."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
