◇ 今日论文 · Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search
① 这是什么
今日论文《今日论文 · Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search》（Zhongwei Yu、Yan Song、Xue Yan、Anjie Liu、Xingyu Lu、Yihang Chen），来自 HF Daily Papers 公开源。
② 值不值得用
进入 HF 每日精选说明有社区关注度；是否与你的问题相关需要读原文判断，本条目不评价研究质量。
③ 怎么开始
先读摘要，需要再读全文（https://huggingface.co/papers/2608.15669）；对照论文 ID（2608.15669）可找实现与讨论。
展开：④ 关键证据 / ⑤ 注意事项与坑
④ 关键证据
- 论文 ID 2608.15669
- 作者 Zhongwei Yu、Yan Song、Xue Yan、Anjie Liu、Xingyu Lu、Yihang Chen
⑤ 注意事项与坑
摘要来自作者原文，未做同行评议级核验；引用请以正式发表版本为准。
适合：追踪今日 AI 论文前沿的读者。
不适合：需要完整复现实验细节的场景（请读原文）。
状态：机检通过（结构与溯源校验）；功能未逐项实测（未校验）。
最小验证（3 步）
- 读摘要 — Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search
- 核作者/日期 — Zhongwei Yu, Yan Song, Xue Yan · 2026-08-16
- 跑 CLI — npx aiskillready search 15669
可以这样用
npx aiskillready search 15669 # 本站 CLI：真实可跑（aiskillready@0.2.0）
说明：`npx aiskillready` 是本站已发布 CLI（npm aiskillready@0.2.0），命令真实可跑；第三方命令按官方文档给出、未逐一实测，本平台不编造结论。
信任层：机检 / 成本 / 置信度 / schema（展开查看）
相关推荐（应该知道的）
相关推荐（3 条）· 展开更多
◇ 今日论文 · How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks
AI has long assisted scientific research, but the rapid advance of LLMs and agentic scaffolds is reshaping the landscape; a single system can now carry whole-stage research from an initial hypothesis all the way to final published paper, which is a paradigm now referred to as AutoResearch. Existing evaluations reveal little about how these agents operate or where they break down. Tasks are narrowl
相似◇ 今日论文 · Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift
Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA), which reinforces noise rather than signal, or on prompt tuning that requires privileged noise annotations unavailable at inference. We address these failures with PRISM (Prototype-Rectified Iterative Self-supervised Mani
相似◇ 今日论文 · MOSS-VL Technical Report
We present MOSS-VL, an open vision-language model family that treats real-time interaction -- perceiving while it speaks -- as a first-class capability. It is co-designed across the stack: the language decoder attends to vision only through gated cross-attention, so the model can naturally see incoming frames while generating; a synthesized interaction corpus supervises when to speak, when to stay
这条不对 / 我执行报错了？带 entry_id 一键提 Issue，回流后修订版本。
🐞 纠错 / 报错 → 提 IssueAI 区块 · 机器可读 JSON（点击展开）
{
"schema_version": "0.5",
"entry_id": "ASR-PAPER-20260818-2608-15669",
"record_type": "paper",
"title": "今日论文 · Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search",
"observed_at": "2026-08-18",
"source": {
"name": "huggingface.co/api/daily_papers",
"url": "https://huggingface.co/api/daily_papers?limit=10",
"snapshot_hash": "652c1f13fb67dd93f7d60fecc11565d77173419a1e4693958922f4b73738fb42",
"fetched_at": "2026-08-18T10:51:18+00:00"
},
"confidence": "medium",
"human_stream": {
"summary": "Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs. Generative models such as large language models (LLMs) provide expressive priors over such spaces, but their likelihoods and self-assessments are unreliable proxies for the objectives and calibrated epi",
"key_points": [
"论文 ID 2608.15669",
"作者 Zhongwei Yu、Yan Song、Xue Yan、Anjie Liu、Xingyu Lu、Yihang Chen",
"发布 2026-08-16T00:00:00.000Z"
],
"note": "来源为 HuggingFace daily papers 公开 API；完整阅读请走原文链接。",
"what_it_is": "今日论文《今日论文 · Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search》（Zhongwei Yu、Yan Song、Xue Yan、Anjie Liu、Xingyu Lu、Yihang Chen），来自 HF Daily Papers 公开源。",
"worth_it": "进入 HF 每日精选说明有社区关注度；是否与你的问题相关需要读原文判断，本条目不评价研究质量。",
"how_to_start": "先读摘要，需要再读全文（https://huggingface.co/papers/2608.15669）；对照论文 ID（2608.15669）可找实现与讨论。",
"evidence": [
"论文 ID 2608.15669",
"作者 Zhongwei Yu、Yan Song、Xue Yan、Anjie Liu、Xingyu Lu、Yihang Chen"
],
"cautions": "摘要来自作者原文，未做同行评议级核验；引用请以正式发表版本为准。"
},
"ai_stream": {
"structured": {
"paper_id": "2608.15669",
"title": "Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search",
"authors": [
"Zhongwei Yu",
"Yan Song",
"Xue Yan",
"Anjie Liu",
"Xingyu Lu",
"Yihang Chen",
"Huichi Zhou",
"Siyuan Guo",
"Luoyang Sun",
"Sihan Chen",
"Xiangning Yu",
"Jun Wang"
],
"published_at": "2026-08-16T00:00:00.000Z",
"url": "https://huggingface.co/papers/2608.15669",
"source_label": "hf-daily-papers"
},
"raw": [
{
"paper_id": "2608.15669",
"title": "Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search",
"authors": [
"Zhongwei Yu",
"Yan Song",
"Xue Yan",
"Anjie Liu",
"Xingyu Lu",
"Yihang Chen",
"Huichi Zhou",
"Siyuan Guo",
"Luoyang Sun",
"Sihan Chen",
"Xiangning Yu",
"Jun Wang"
],
"summary": "Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs. Generative models such as large language models (LLMs) provide expressive priors over such spaces, but their likelihoods and self-assessments are unreliable proxies for the objectives and calibrated epistemic uncertainty, especially for novel candidates outside the observed data distribution. We introduce the Large Discovery Model (LDM), an empirically grounded recurrent architecture that couples a ",
"published_at": "2026-08-16T00:00:00.000Z",
"submitted_on_daily_at": null,
"url": "https://huggingface.co/papers/2608.15669"
}
]
},
"token_cost": {
"total": 0.0,
"currency": "USD",
"breakdown": {
"crawl": 0.0,
"clean": 0.0,
"elevate": 0.0,
"verify": 0.0
}
},
"machine_verified": true,
"review": {
"status": "agent_reviewed",
"reviewer": "pipeline-validate",
"reviewed_at": "2026-08-18T10:54:20+00:00",
"comments": "机检通过（schema 0 error + 溯源一致 + 成本达标）"
},
"provenance": {
"extracted_by": "codex",
"extracted_at": "2026-08-18T10:53:05+00:00",
"pipeline": "collect_hf_papers.py + build_entries.py v0.2（规则管线）",
"access_urls": [
"https://huggingface.co/api/daily_papers?limit=10"
],
"card_generated_at": "2026-08-18T10:53:05+00:00",
"card_pipeline": "enrich_human_stream.py v0.1（规则模板，零 Token）"
}
}