{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.08605", "kind": "paper", "url": "https://arxiv.org/abs/2608.08605"}], "authors": ["Guo Chen", "Ziwen Li", "Reed Li", "Yu Lu", "Haibo Shi", "Bingbing Xu", "Junjie Huang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.08605", "source_url": "https://arxiv.org/abs/2608.08605"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "ForestBench evaluates multi-agent collaboration by representing MAS traces as unified collaboration graphs, comparing them against query-specific reference forests of successful graphs, and scoring structural similarity with a metric panel."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.08605", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.08605", "title": "ForestBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Southwest University", "Tencent (China)", "Chinese Academy of Sciences", "Institute of Computing Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.08605", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.08605", "source_url": "https://openalex.org/W7202162868"}, "key": "claire-radar:2608.08605", "modality": null, "name": "ForestBench", "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": "true", "origin_record_id": "bm_forestbench_98bb6077", "origin_source": "arxiv", "recognition_confidence": "0.65", "record_sha256": "165cb8ba755a4e750452541808cc44fa13be1b99e75c44e585926d2705c1bf45", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-03T09:03:47.731241Z", "source_url": "https://arxiv.org/abs/2608.08605"}, "publisher": null, "released": "2026-08-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.08605", "source_url": "https://arxiv.org/abs/2608.08605"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-08605", "source": "claire_radar", "source_benchmark_id": "2608.08605", "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/2608.08605", "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": "Low", "horizon": "7d", "reason": "The structural evaluation approach could interest multi-agent researchers, but the absence of an explicit code or data link in the supplied evidence may slow initial adoption.", "score": 55}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-03T09:03:47.731241Z", "inputHash": "b713670aa8c44775c4a4cfb6619bad0fa12574d2c9274a81c1722978f0f15d56", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "Instantiating the framework as ForestBench, we filter $844$ collaboration-necessary queries from seven public datasets, precompute ten successful target-conditioned reference graphs per query, and evaluate six representative MAS frameworks.", "canonicalNameSource": "abstract", "decisionReason": "The benchmark defines a fixed set of filtered queries, precomputed reference forests, and a deterministic scoring protocol; it is reusable as a public evaluation framework even though the paper does not currently list a separate artifact link.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-03T09:03:47.731241Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ForestBench evaluates multi-agent collaboration by representing MAS traces as unified collaboration graphs, comparing them against query-specific reference forests of successful graphs, and scoring structural similarity with a metric panel.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "evaluation protocol evidence"], "snippet": "Each forest is a benchmark-provided collection of verified-success graphs: it records diverse ways in which representative MAS methods can complete the task, rather than prescribing a unique optimal process."}, "familyId": "bmf_10870d39ebd2", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_forestbench_98bb6077", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.08605", "pdf": "https://arxiv.org/pdf/2608.08605", "project": null, "report": "https://arxiv.org/abs/2608.08605"}, "metrics": [], "motivation": "Multi-agent systems (MAS) built on Large Language Models (LLMs) are proliferating rapidly, but their heterogeneous execution traces provide no common basis for evaluation across methods.", "name": "ForestBench", "oneLine": "ForestBench evaluates multi-agent collaboration by representing MAS traces as unified collaboration graphs, comparing them against query-specific reference forests of successful graphs, and scoring structural similarity with a metric panel.", "paperTitle": "ForestBench: A Unified Graph Framework for Evaluating Multi-Agent Collaboration", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.08605", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "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": 0.65, "relation": "introduces", "releasedAt": "2026-08-09", "source": {"authors": ["Guo Chen", "Ziwen Li", "Reed Li", "Yu Lu", "Haibo Shi", "Bingbing Xu", "Junjie Huang"], "categories": ["cs.AI"], "id": "2608.08605", "title": "ForestBench: A Unified Graph Framework for Evaluating Multi-Agent Collaboration", "type": "arxiv", "url": "https://arxiv.org/abs/2608.08605"}, "sourceUpdatedAt": "2026-08-11T07:14:11Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "It provides a common structural representation for heterogeneous MAS outputs, enabling fast, LLM-free, reproducible cross-method comparisons of collaboration quality."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
