{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.13681", "kind": "paper", "url": "https://arxiv.org/abs/2606.13681"}, {"id": "gh:aiden0526/evoarena", "kind": "repo", "url": "https://github.com/Aiden0526/EvoArena"}], "categories": ["Agents & Tool Use", "General AI", "cs.CL"], "description": {"en": "EvoArena is a benchmark suite for LLM agents in dynamic environments, covering terminal workflows, software repositories, and social preferences. It evaluates step and chain accuracy under progressive environment updates."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.13681", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.13681", "title": "EvoArena"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.13681", "modality": null, "name": "EvoArena", "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_evoarena_70b33a0d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b8964054eadedb2d164f54c1c4df2fe504506a3da8063f2b2ffc81568d82ce27", "relation": "aggregates", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.13681"}, "publisher": null, "released": "2026-06-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.13681", "source_url": "https://arxiv.org/abs/2606.13681"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-13681", "source": "claire_radar", "source_benchmark_id": "2606.13681", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Aiden0526/EvoArena", "githubScope": "benchmark_repo", "githubStars": 26, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 146, "hfPaperUrl": "https://huggingface.co/papers/2606.13681", "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": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "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": "b867bf3a4511c256aa422e7d59d8b6e44ef587e04b2a370e8d4b6bb124f6271c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EvoArena is a benchmark suite for LLM agents in dynamic environments, covering terminal workflows, software repositories, and social preferences. It evaluates step and chain accuracy under progressive environment updates.", "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"], "snippet": "To address this gap, we introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains."}, "familyId": "bmf_75e1fa5bb7d6", "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/Aiden0526/EvoArena", "url": "https://github.com/Aiden0526/EvoArena"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Aiden0526/EvoArena", "url": "https://huggingface.co/papers/2606.13681"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/Aiden0526/EvoArena", "url": "https://huggingface.co/api/papers/2606.13681"}], "scope": "benchmark_repo", "url": "https://github.com/Aiden0526/EvoArena", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_evoarena_70b33a0d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Aiden0526/EvoArena", "data": null, "hfPaper": "https://huggingface.co/papers/2606.13681", "paper": "https://arxiv.org/abs/2606.13681", "pdf": "https://arxiv.org/pdf/2606.13681", "project": null, "report": "https://arxiv.org/abs/2606.13681"}, "metrics": [], "motivation": "Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments.", "name": "EvoArena", "oneLine": "EvoArena is a benchmark suite for LLM agents in dynamic environments, covering terminal workflows, software repositories, and social preferences. It evaluates step and chain accuracy under progressive environment updates.", "paperTitle": "EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.13681", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "EvoArena Project", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Aiden0526/EvoArena"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "aggregates", "releasedAt": "2026-06-11", "source": {"authors": ["Jundong Xu", "Qingchuan Li", "Jiaying Wu", "Yihuai Lan", "Shuyue Stella Li", "Huichi Zhou", "Bowen Jiang", "Lei Wang", "Jun Wang", "Anh Tuan Luu", "Caiming Xiong", "Hae Won Park", "Bryan Hooi", "Zhiyuan Hu"], "categories": ["cs.CL"], "id": "2606.13681", "title": "EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments", "type": "arxiv", "url": "https://arxiv.org/abs/2606.13681"}, "sourceUpdatedAt": "2026-06-17T04:10:52Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Real-world deployments are dynamic, and existing benchmarks often ignore environment evolution. EvoArena provides a protocol for evaluating agent adaptation and highlights the need for memory models that track changes."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
