{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.31111", "kind": "paper", "url": "https://arxiv.org/abs/2608.31111"}, {"kind": "website", "url": "https://self-developing-agents.github.io/"}], "authors": ["Yuhao Wu", "Jingyuan Zhang", "Jiajun Shi", "Yuxuan Zhang", "Xinping Lei", "Junting Zhou", "Zexuan Wang", "Yuchen Wu", "Huan Zhou", "Duo Wang", "Yinzhu Piao", "Yongchang Peng", "Yunfeng Shi", "Jin Chen", "Zuo Wang", "Jinkai Liu", "Jiaheng Liu", "Wenxuan Zhang", "Shen Yan", "Wenhao Huang", "Ge Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.31111", "source_url": "https://arxiv.org/abs/2608.31111"}, "categories": ["General AI", "Language & Knowledge", "Self-Evolution"], "description": {"en": "ASPIRE evaluates LLM agents and models on self-evolution from vague natural-language goals, using a hidden expert-authored set of 520 items across six goals in an interactive environment."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.31111", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.31111", "title": "ASPIRE"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Singapore University of Technology and Design"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.31111", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.31111", "source_url": "https://openalex.org/W7204903604"}, "key": "claire-radar:2608.31111", "modality": null, "name": "ASPIRE", "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_aspire_c720473f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7afe0032b1dfd88ba144d6353f5494e256bdab4d870f51a717e2a5ec627670e7", "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/2608.31111"}, "publisher": null, "released": "2026-08-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.31111", "source_url": "https://arxiv.org/abs/2608.31111"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-31111", "source": "claire_radar", "source_benchmark_id": "2608.31111", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.31111", "observedAt": "2026-08-31T04:56:28.279469Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T05:12:51.621571Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The novel vague-goal self-evolution framing and interactive benchmark scope are likely to attract moderate interest from the LLM agent community within the first week.", "score": 55}, "capabilities": [], "confidence": "High", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "ebf56b9ffa5359b38e39693f4ee73d92f4c8c0531c0aac54a5a8387d50e4d154", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution.", "canonicalNameSource": "abstract", "decisionReason": "The paper explicitly introduces ASPIRE as a benchmark with hidden evaluation items and a scoring setup, and provides a project page for public access, supporting formal release.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ASPIRE evaluates LLM agents and models on self-evolution from vague natural-language goals, using a hidden expert-authored set of 520 items across six goals in an interactive environment.", "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 ASPIRE, a benchmark for vague-goal-driven self-evolution."}, "familyId": "bmf_bfe0a8205d19", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_aspire_c720473f", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.31111", "pdf": "https://arxiv.org/pdf/2608.31111", "project": "https://self-developing-agents.github.io/", "report": "https://arxiv.org/abs/2608.31111"}, "metrics": [], "motivation": "Many important forms of human learning begin with a vague goal, such as \"become a better physicist\" or \"improve at research.\" Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether they have actually improved.", "name": "ASPIRE", "oneLine": "ASPIRE evaluates LLM agents and models on self-evolution from vague natural-language goals, using a hidden expert-authored set of 520 items across six goals in an interactive environment.", "paperTitle": "Aspire: Can Models Self-Evolve from Vague Goals?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.31111", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "publications": [], "ranking": {"30d": {"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": 30}, "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}, "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": "2026-08-31", "source": {"authors": ["Yuhao Wu", "Jingyuan Zhang", "Jiajun Shi", "Yuxuan Zhang", "Xinping Lei", "Junting Zhou", "Zexuan Wang", "Yuchen Wu", "Huan Zhou", "Duo Wang", "Yinzhu Piao", "Yongchang Peng", "Yunfeng Shi", "Jin Chen", "Zuo Wang", "Jinkai Liu", "Jiaheng Liu", "Wenxuan Zhang", "Shen Yan", "Wenhao Huang", "Ge Zhang"], "categories": ["cs.CL"], "id": "2608.31111", "title": "Aspire: Can Models Self-Evolve from Vague Goals?", "type": "arxiv", "url": "https://arxiv.org/abs/2608.31111"}, "sourceUpdatedAt": "2026-08-31T17:14:59Z", "topics": ["Self-Evolution"], "venueAttempts": [], "whyItMatters": "It fills a gap in evaluating how systems interpret vague goals, select their own training signals, and decide when to evaluate, rather than optimizing predefined metrics, offering a more realistic test of autonomous improvement."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
