{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.26791", "kind": "paper", "url": "https://arxiv.org/abs/2607.26791"}, {"kind": "repo", "url": "https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond"}], "authors": ["Lehan Wang", "Boli Chen", "Ruixue Ding", "Pengjun Xie", "Jinwei Huang", "Zhendong Liu", "Shuo Wang", "Tao Lei", "Xin Ouyang", "Xiaomeng Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.26791", "source_url": "https://arxiv.org/abs/2607.26791"}, "categories": ["Cybersecurity", "Language & Knowledge", "cs.CR"], "description": {"en": "A benchmark for evaluating LLM agents on post-compromise incident-response workflows using forensic disk snapshots and host security reports across 10 cyber ranges."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.26791", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.26791", "title": "SecRespond"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Hong Kong University of Science and Technology", "Alibaba Group (Cayman Islands)", "Alibaba Group (China)", "Alibaba Group (United States)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.26791", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.26791", "source_url": "https://openalex.org/W7171834298"}, "key": "claire-radar:2607.26791", "modality": null, "name": "SecRespond", "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_secrespond_a48429f2", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f52511499b21f7364ad427a7ed858553ccc0ca3adf51f4ee24401dc266294e6d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.26791"}, "publisher": null, "released": "2026-07-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.26791", "source_url": "https://arxiv.org/abs/2607.26791"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-26791", "source": "claire_radar", "source_benchmark_id": "2607.26791", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Cybersecurity"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Alibaba-NLP/qqr", "githubScope": "hosting_repo", "githubStars": 314, "hfDailySubmittedAt": "2026-07-30T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 3, "hfPaperUrl": "https://huggingface.co/papers/2607.26791", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "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": "6f9ef85dd26044adf9cfbb4910f7395137fb5d60b1f2112ec1964a99e2556f2f", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A benchmark for evaluating LLM agents on post-compromise incident-response workflows using forensic disk snapshots and host security reports across 10 cyber ranges.", "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", "public artifact URL"], "snippet": "To address this gap, we introduce SecRespond, the first benchmark for evaluating LLM agents on the post-compromise incident-response workflow."}, "familyId": "bmf_9705c5bae016", "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/Alibaba-NLP/qqr/tree/main/data/secrespond", "url": "https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Alibaba-NLP/qqr", "url": "https://huggingface.co/papers/2607.26791"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond.", "url": "https://arxiv.org/abs/2607.26791"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond", "url": "https://arxiv.org/abs/2607.26791"}], "scope": "hosting_repo", "url": "https://github.com/Alibaba-NLP/qqr", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_secrespond_a48429f2", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Cybersecurity"], "links": {"code": "https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond", "data": null, "hfPaper": "https://huggingface.co/papers/2607.26791", "paper": "https://arxiv.org/abs/2607.26791", "pdf": "https://arxiv.org/pdf/2607.26791", "project": null, "report": "https://arxiv.org/abs/2607.26791"}, "metrics": [], "motivation": "Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities.", "name": "SecRespond", "oneLine": "A benchmark for evaluating LLM agents on post-compromise incident-response workflows using forensic disk snapshots and host security reports across 10 cyber ranges.", "paperTitle": "SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response", "primaryDomain": "Cybersecurity", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.26791", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Alibaba NLP", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.24495074076910422, "value": 3}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 46}, "method": "attention-ranking-v13", "rank": null, "score": 46}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-29", "source": {"authors": ["Lehan Wang", "Boli Chen", "Ruixue Ding", "Pengjun Xie", "Jinwei Huang", "Zhendong Liu", "Shuo Wang", "Tao Lei", "Xin Ouyang", "Xiaomeng Li"], "categories": ["cs.CR", "cs.AI", "cs.CL"], "id": "2607.26791", "title": "SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response", "type": "arxiv", "url": "https://arxiv.org/abs/2607.26791"}, "sourceUpdatedAt": "2026-07-29T11:32:23Z", "topics": ["cs.CR"], "venueAttempts": [], "whyItMatters": "Cybersecurity benchmarks typically focus on pre-compromise settings; this addresses the gap in evaluating agents for real-world incident response, where proactive investigation and remediation are critical."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
