{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.23179", "kind": "paper", "url": "https://arxiv.org/abs/2608.23179"}], "authors": ["Chang Liu", "Xiaohui Xie", "Xinyi Chen", "Yong Cui"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.23179", "source_url": "https://arxiv.org/abs/2608.23179"}, "categories": ["General AI", "Language & Knowledge", "cs.NI"], "description": {"en": "Evaluates LLM agents in closed-loop network configuration across 480 task instances from 96 protocol-focused templates, scoring based on hidden executable test cases."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.23179", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.23179", "title": "NetConfArena"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tsinghua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.23179", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.23179", "source_url": "https://openalex.org/W7204209332"}, "key": "claire-radar:2608.23179", "modality": null, "name": "NetConfArena", "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": "true", "origin_record_id": "bm_netconfarena_7ff1c051", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7beff847df3a7c70d6a25c4f205e244c54e879b268f4a907a13f3e83234f518c", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:10:57.123445Z", "source_url": "https://arxiv.org/abs/2608.23179"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.23179", "source_url": "https://arxiv.org/abs/2608.23179"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-23179", "source": "claire_radar", "source_benchmark_id": "2608.23179", "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/2608.23179", "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"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark addresses a critical infrastructure domain with an interactive evaluation setting, likely to attract interest from both LLM agent and networking communities.", "score": 70}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:10:57.123445Z", "inputHash": "27780fd4b840aab3604da4511364f72da1c3c435fc5d1b74b2f4b48aa9a504af", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We present NetConfArena, an executable benchmark for evaluating LLM agents in closed-loop network configuration.", "canonicalNameSource": "abstract", "decisionReason": "The paper presents a named, executable benchmark with a clear evaluation protocol and public availability, indicating an ongoing public benchmark for model comparison.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:10:57.123445Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLM agents in closed-loop network configuration across 480 task instances from 96 protocol-focused templates, scoring based on hidden executable test cases.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present NetConfArena, an executable benchmark for evaluating LLM agents in closed-loop network configuration."}, "familyId": "bmf_78cd2ef5a953", "firstSeenAt": "2026-08-26", "heat": null, "id": "bm_netconfarena_7ff1c051", "indexedAt": "2026-08-26T06:08:22.244942Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.23179", "pdf": "https://arxiv.org/pdf/2608.23179", "project": null, "report": "https://arxiv.org/abs/2608.23179"}, "metrics": [], "motivation": "Large language model (LLM) agents are increasingly attractive for automating network configuration, yet their reliability and failure patterns are poorly understood.", "name": "NetConfArena", "oneLine": "Evaluates LLM agents in closed-loop network configuration across 480 task instances from 96 protocol-focused templates, scoring based on hidden executable test cases.", "paperTitle": "NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.23179", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-26T06:08:22.244942Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Chang Liu", "Xiaohui Xie", "Xinyi Chen", "Yong Cui"], "categories": ["cs.NI", "cs.AI"], "id": "2608.23179", "title": "NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration", "type": "arxiv", "url": "https://arxiv.org/abs/2608.23179"}, "sourceUpdatedAt": "2026-08-24T12:26:37Z", "topics": ["cs.NI"], "venueAttempts": [], "whyItMatters": "Provides a realistic, executable benchmark for network configuration agents, revealing failure patterns and guiding improvements in agent reliability and planning."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
