{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.14574", "kind": "paper", "url": "https://arxiv.org/abs/2606.14574"}], "authors": ["Xiaoxin Lu", "Ranran Haoran Zhang", "Rui Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.14574", "source_url": "https://arxiv.org/abs/2606.14574"}, "categories": ["General AI", "Language & Knowledge", "Planning", "cs.CL"], "description": {"en": "SIMMER evaluates latent failures in LLM-generated plans for kitchen-domain tasks using a curated symbolic world model with 77 actions and 262 objects, scoring error-free plans and latent hazard detection."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.14574", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.14574", "title": "SIMMER"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Pennsylvania State University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.14574", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.14574", "source_url": "https://openalex.org/W7164837075"}, "key": "claire-radar:2606.14574", "modality": null, "name": "SIMMER", "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_simmer_2d9d2c96", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b773c5ddd6b48f67daf9ae2fbdb8c10258f0043ec67dd667a75e06549459d4ac", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.14574"}, "publisher": null, "released": "2026-06-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.14574", "source_url": "https://arxiv.org/abs/2606.14574"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-14574", "source": "claire_radar", "source_benchmark_id": "2606.14574", "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/2606.14574", "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": ["Planning"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "354641bae5f4dfcc81b7856be20ae40c7a1448dfa8fe7042ce46c55500d3bc10", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SIMMER evaluates latent failures in LLM-generated plans for kitchen-domain tasks using a curated symbolic world model with 77 actions and 262 objects, scoring error-free plans and latent hazard detection.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "To address this gap, we introduce SIMMER, a benchmark for evaluating latent failures in LLM planning through a human-curated symbolic world model grounded in the kitchen domain."}, "familyId": "bmf_365fcc9a87e9", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_simmer_2d9d2c96", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.14574", "paper": "https://arxiv.org/abs/2606.14574", "pdf": "https://arxiv.org/pdf/2606.14574", "project": null, "report": "https://arxiv.org/abs/2606.14574"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments.", "name": "SIMMER", "oneLine": "SIMMER evaluates latent failures in LLM-generated plans for kitchen-domain tasks using a curated symbolic world model with 77 actions and 262 objects, scoring error-free plans and latent hazard detection.", "paperTitle": "SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model", "primaryDomain": "General AI", "publication": {"evidence": "Accepted at COLM 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.14574", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "COLM 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-12", "source": {"authors": ["Xiaoxin Lu", "Ranran Haoran Zhang", "Rui Zhang"], "categories": ["cs.CL", "cs.AI"], "id": "2606.14574", "title": "SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model", "type": "arxiv", "url": "https://arxiv.org/abs/2606.14574"}, "sourceUpdatedAt": "2026-08-09T04:57:47Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Accepted at COLM 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted at COLM 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.14574"}], "reviewStatus": "accepted", "venueName": "COLM 2026"}], "whyItMatters": "Existing plan benchmarks miss failures that don't immediately halt execution but compromise goals; SIMMER provides metrics for irreversible latent failures, important for safe deployment of LLM planners."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
