{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.15532", "kind": "paper", "url": "https://arxiv.org/abs/2606.15532"}], "authors": ["Rongzhi Zhu", "Xiang Huang", "Yuchuan Wu", "Rui Wang", "Zequn Sun", "Tao Ren", "Weiyao Luo", "Bingxue Qiu", "Jieping Ye", "Yongbin Li", "Wei Hu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.15532", "source_url": "https://arxiv.org/abs/2606.15532"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "EIBench is a simulator-based benchmark for interactive emotion management, containing 2,222 scenarios across a 2x2 taxonomy of Support, Defense, Repair, and Charm. It evaluates LLM agents on multi-turn dialogue where a user simulator updates emotion-relation states and provides anchor-based scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.15532", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.15532", "title": "EIBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.15532", "modality": null, "name": "EIBench", "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_eibench_cb3bf853", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "586dd9fd3362d2f82bba46881ccfc0621d87f3fb1ea852352505b6cbe40283fe", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.15532"}, "publisher": null, "released": "2026-06-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.15532", "source_url": "https://arxiv.org/abs/2606.15532"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-15532", "source": "claire_radar", "source_benchmark_id": "2606.15532", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.15532", "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", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "status": "stale"}, "capabilities": [], "confidence": "High", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "f83dd1f01dbe8123af75524a9e92e5e33cf36cd022a2ea59799fa35048fcb238", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EIBench is a simulator-based benchmark for interactive emotion management, containing 2,222 scenarios across a 2x2 taxonomy of Support, Defense, Repair, and Charm. It evaluates LLM agents on multi-turn dialogue where a user simulator updates emotion-relation states and provides anchor-based scoring.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce EIBench, a simulator-based benchmark for interactive emotion management."}, "familyId": "bmf_1505489eac0d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_eibench_cb3bf853", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.15532", "paper": "https://arxiv.org/abs/2606.15532", "pdf": "https://arxiv.org/pdf/2606.15532", "project": null, "report": "https://arxiv.org/abs/2606.15532"}, "metrics": [], "motivation": "Emotional intelligence (EI) in Large Language Models (LLMs) is often evaluated through static understanding tasks or single-response dialogue generation.", "name": "EIBench", "oneLine": "EIBench is a simulator-based benchmark for interactive emotion management, containing 2,222 scenarios across a 2x2 taxonomy of Support, Defense, Repair, and Charm. It evaluates LLM agents on multi-turn dialogue where a user simulator updates emotion-relation states and provides anchor-based scoring.", "paperTitle": "EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.15532", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-14", "source": {"authors": ["Rongzhi Zhu and Xiang Huang and Yuchuan Wu and Rui Wang and Zequn Sun and Tao Ren and Weiyao Luo and Bingxue Qiu and Jieping Ye and Yongbin Li and Wei Hu"], "categories": ["cs.CL", "cs.LG"], "id": "2606.15532", "title": "EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management", "type": "arxiv", "url": "https://arxiv.org/abs/2606.15532"}, "sourceUpdatedAt": "2026-06-14T01:22:03Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "EIBench fills the gap in evaluating emotional intelligence beyond static understanding, focusing on interactive emotion management over multiple turns. Its simulator provides both outcome and dense turn-level feedback, enabling training and evaluation in a unified environment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
