{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.29397", "kind": "paper", "url": "https://arxiv.org/abs/2608.29397"}, {"id": "gh:xzx34/algoworlds", "kind": "repo", "url": "https://github.com/xzx34/AlgoWorlds"}, {"kind": "website", "url": "https://xzx34.github.io/AlgoWorlds/"}], "authors": ["Zixiang Xu", "Jiaan Wang", "Fandong Meng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.29397", "source_url": "https://arxiv.org/abs/2608.29397"}, "categories": ["Agents", "Agents & Tool Use", "General AI", "Tool use"], "description": {"en": "Evaluates language-model agents on 240 algorithmic worlds across ten combinatorial optimization families, assessing structured final decisions for feasibility and exact global optimality using certified optima."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.29397", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.29397", "title": "AlgoWorlds"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.29397", "modality": null, "name": "AlgoWorlds", "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_algoworlds_02d60d03", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f11e406b6cced5ec3a40324427087dd429e0b5059e3e18f106b800a8d5164e55", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.29397"}, "publisher": null, "released": "2026-08-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.29397", "source_url": "https://arxiv.org/abs/2608.29397"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-29397", "source": "claire_radar", "source_benchmark_id": "2608.29397", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": "https://github.com/xzx34/AlgoWorlds", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.29397", "observedAt": "2026-09-02T05:12:51.621571Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-02T05:12:51.621571Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T05:12:51.621571Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The combination of a novel global optimization focus, inclusion of leading LLMs, and available code and project page suggests moderate early interest in the research community.", "score": 65}, "capabilities": ["Tool use"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "71a61a7d972516d83e1b18c4aad2cfc8d79e83feb1c31f3e65a7178d052172f0", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark provides a frozen release with a defined primary metric (Exact optimality), a public runner, and a scorer, supporting ongoing comparisons across model submissions.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates language-model agents on 240 algorithmic worlds across ten combinatorial optimization families, assessing structured final decisions for feasibility and exact global optimality using certified optima.", "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", "public artifact URL"], "snippet": "We introduce AlgoWorlds, a benchmark that transforms formally specified combinatorial optimization problems into partially observed decision environments with verifiable global optima."}, "familyId": "bmf_b3b02dd71e67", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_algoworlds_02d60d03", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": [], "links": {"code": "https://github.com/xzx34/AlgoWorlds", "data": null, "hfPaper": "https://huggingface.co/papers/2608.29397", "paper": "https://arxiv.org/abs/2608.29397", "pdf": "https://arxiv.org/pdf/2608.29397", "project": "https://xzx34.github.io/AlgoWorlds/", "report": "https://arxiv.org/abs/2608.29397"}, "metrics": [], "motivation": "Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments.", "name": "AlgoWorlds", "oneLine": "Evaluates language-model agents on 240 algorithmic worlds across ten combinatorial optimization families, assessing structured final decisions for feasibility and exact global optimality using certified optima.", "paperTitle": "AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.29397", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T00:50:41.903960Z"}, "publications": [], "publishers": [{"name": "Weixin AI", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/xzx34/AlgoWorlds"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 127, "score": 23}, "method": "attention-ranking-v13", "rank": 127, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 320, "score": 23}, "method": "attention-ranking-v13", "rank": 320, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-29", "source": {"authors": ["Zixiang Xu", "Jiaan Wang", "Fandong Meng"], "categories": ["cs.CL"], "id": "2608.29397", "title": "AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds", "type": "arxiv", "url": "https://arxiv.org/abs/2608.29397"}, "sourceUpdatedAt": "2026-08-29T18:37:41Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Addresses the gap between tool-use feasibility and global optimality in interdependent decision settings, providing a reproducible standard for comparing agents' ability to reason under shared constraints and verify optimal decisions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
