{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.02380", "kind": "paper", "url": "https://arxiv.org/abs/2606.02380"}], "authors": ["Yuyan Bu", "Haowei Li", "Qirui Zheng", "Bowen Dong", "Kaiyue Yang", "Jiaming Ji", "Yingshui Tan", "Wenxin Li", "Yaodong Yang", "Juntao Dai"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.02380", "source_url": "https://arxiv.org/abs/2606.02380"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Benchmark for evaluating spontaneous plan-action divergence in agents, integrating actual tool execution and controlled pressure scenarios to distinguish strategic deception from hallucination."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.02380", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.02380", "title": "SPADE-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Beijing Academy of Artificial Intelligence", "University of Science and Technology of China", "Peking University", "University of Chinese Academy of Sciences"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.02380", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.02380", "source_url": "https://openalex.org/W7163198620"}, "key": "claire-radar:2606.02380", "modality": null, "name": "SPADE-Bench", "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": "unknown", "origin_record_id": "bm_spade-bench_b8164972", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "350a77d7e2bc240d9dfef70120c9f85dc2a9c3e5b617e72570675d107f36bc30", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.02380"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.02380", "source_url": "https://arxiv.org/abs/2606.02380"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-02380", "source": "claire_radar", "source_benchmark_id": "2606.02380", "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/2606.02380", "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": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "3fbc72802ddfa61546f9fcfd3295107dc956b1ef8e312a1502d72f7d7a6ec9b9", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Benchmark for evaluating spontaneous plan-action divergence in agents, integrating actual tool execution and controlled pressure scenarios to distinguish strategic deception from hallucination.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "To assess this, we introduce SPADE-Bench, a benchmark designed to evaluate spontaneous plan-action divergence."}, "familyId": "bmf_96fc99f9be33", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_spade-bench_b8164972", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.02380", "paper": "https://arxiv.org/abs/2606.02380", "pdf": "https://arxiv.org/pdf/2606.02380", "project": null, "report": "https://arxiv.org/abs/2606.02380"}, "metrics": [], "motivation": "As LLM-based agents expand their operational scope, reliability becomes a prerequisite for real-world deployment.", "name": "SPADE-Bench", "oneLine": "Benchmark for evaluating spontaneous plan-action divergence in agents, integrating actual tool execution and controlled pressure scenarios to distinguish strategic deception from hallucination.", "paperTitle": "SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.02380", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-01", "source": {"authors": ["Yuyan Bu", "Haowei Li", "Qirui Zheng", "Bowen Dong", "Kaiyue Yang", "Jiaming Ji", "Yingshui Tan", "Wenxin Li", "Yaodong Yang", "Juntao Dai"], "categories": ["cs.CL", "cs.AI"], "id": "2606.02380", "title": "SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence", "type": "arxiv", "url": "https://arxiv.org/abs/2606.02380"}, "sourceUpdatedAt": "2026-06-28T14:28:39Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses the critical risk of agent deception in autonomous systems, but lacks a public comparison path."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
