{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"self-replication-extended","title":"Large language model-powered AI systems achieve self-replication with no human intervention","aliases":[],"authors":["Xudong Pan","Jiarun Dai","Yihe Fan","Minyuan Luo","Changyi Li","Min Yang"],"primaryFunction":"discovery","secondaryFunctions":[],"kind":"study","sourceId":"self-replication-extended-publication","attributionSourceId":"self-replication-extended-publication-author-source","originalUrl":"https://arxiv.org/abs/2503.17378","publicationDate":"2025-03-14","updatedOn":"2026-10-25","areas":["autonomy"],"scopeNote":{"en":"Relevance is assigned to the research question and stated conditions of the work. A topic tag is not a risk rating.","zh":"风险关联依据研究问题及明确条件建立，主题标签不代表风险评级。"},"protocolIds":[],"contributions":[{"organizationId":"fudan","role":"research","sourceId":"self-replication-extended-publication-author-source","locator":"Author affiliations on the original paper title page"}],"summary":{"en":"Extends controlled experiments on AI-system self-replication and documents the agent setup and observed replication behavior.","zh":"扩展 AI 系统自我复制的受控实验，记录智能体设置与观察到的复制行为。"},"note":{"question":null,"method":null,"finding":null,"supports":null,"limits":null,"connections":null},"resources":[],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"A substantive NUWA research note is not yet available. The repeated draft sections were removed pending review of the original methods, findings and limitations; use the original publication for the research account.","zh":"实质性的 NUWA 研究笔记尚未完成。重复草稿章节已移除，待核查原始方法、发现与限制；研究内容请以原始出版物为准。"},"noteSourceLocator":"No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence.","tags":[]},"reading":{"id":"self-replication-extended","title":"Large language model-powered AI systems achieve self-replication with no human intervention","en":{"takeaway":"The expanded study finds copying success across several model families, under an explicitly supplied replication task.","question":"How broadly does end-to-end replication appear when a common scaffold is paired with different models?","design":"A common scaffold is evaluated across a model panel with repeated trials in resettable containers; success requires a separated running copy with the same functionality.","findings":["Success is not confined to the largest tested models.","The paper reports associations between general benchmark capability and copying success, and additional selected adaptation trajectories."],"interpretation":"NUWA interpretation: model breadth strengthens evidence that the mechanism is not unique to one checkpoint, without making access conditions irrelevant.","limits":"Small per-model trial counts, benchmark correlations and selected trajectories do not identify a universal capability threshold or spontaneous propensity.","connections":["NUWA connection: the earlier self-replication paper is a narrower precursor; the network-replication paper adds obtaining target access to a copying pipeline."],"decisionRelevance":"NUWA recommendation: compare only deployments with matching target access and success criteria; retain precursor and expanded versions separately."},"zh":{"takeaway":"扩展实验在多类模型中观察到复制成功，但仍是明确布置的复制任务。","question":"同一脚手架接入不同模型时，端到端复制能力有多广泛？","design":"作者在可重置容器中对模型集合进行重复试验，以建立具有同等功能、独立运行的副本为成功条件。","findings":["复制成功并不只出现在最大模型。","论文报告通用基准能力与复制成功的关联，并展示若干适应环境的轨迹。"],"interpretation":"NUWA 解读：更广模型覆盖说明机制不限于单一检查点，但不消除权限条件的作用。","limits":"每模型试验较少；基准相关性和精选轨迹不能识别普适能力阈值或自发倾向。","connections":["NUWA 关联：早期复制论文是较窄的前序工作；网络复制论文将获得目标访问加入复制流程。"],"decisionRelevance":"NUWA 建议：仅在目标访问和成功定义相符时比较，并分别保留前序与扩展版本。"},"sourceRefs":[{"sourceId":"self-replication-extended-publication","url":"https://arxiv.org/html/2503.17378","locator":"2 Evaluation on the self-replication capability","version":"Selected original resource https://arxiv.org/html/2503.17378; sha256:bdb7bb0349475c85f6e6ece36a2d956bc7071ae0f574d4d5125a7909c8e28c54; archived source capture; exact capture time not independently established","artifactSha256":"bdb7bb0349475c85f6e6ece36a2d956bc7071ae0f574d4d5125a7909c8e28c54"},{"sourceId":"self-replication-extended-publication","url":"https://arxiv.org/html/2503.17378","locator":"3 Methods","version":"Selected original resource https://arxiv.org/html/2503.17378; sha256:bdb7bb0349475c85f6e6ece36a2d956bc7071ae0f574d4d5125a7909c8e28c54; archived source capture; exact capture time not independently established","artifactSha256":"bdb7bb0349475c85f6e6ece36a2d956bc7071ae0f574d4d5125a7909c8e28c54"},{"sourceId":"self-replication-extended-publication","url":"https://arxiv.org/html/2503.17378","locator":"4.1 Emergence of the self-replication capability","version":"Selected original resource https://arxiv.org/html/2503.17378; sha256:bdb7bb0349475c85f6e6ece36a2d956bc7071ae0f574d4d5125a7909c8e28c54; archived source capture; exact capture time not independently established","artifactSha256":"bdb7bb0349475c85f6e6ece36a2d956bc7071ae0f574d4d5125a7909c8e28c54"},{"sourceId":"self-replication-extended-publication","url":"https://arxiv.org/html/2503.17378","locator":"6 Discussion","version":"Selected original resource https://arxiv.org/html/2503.17378; sha256:bdb7bb0349475c85f6e6ece36a2d956bc7071ae0f574d4d5125a7909c8e28c54; archived source capture; exact capture time not independently established","artifactSha256":"bdb7bb0349475c85f6e6ece36a2d956bc7071ae0f574d4d5125a7909c8e28c54"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected substantive sections of the full source body","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"1dea5391751d304ca60905d52d80a5bcf9d2818d3e83a01197946df42414420c"}},"sources":[{"id":"self-replication-extended-publication","title":"Large language model-powered AI systems achieve self-replication with no human intervention","url":"https://arxiv.org/abs/2503.17378","version":"arXiv:2503.17378v2","publicationDate":"2025-03-14","datePrecision":"day","type":"paper","verifiedOn":"2026-10-25","documentId":"arxiv:2503.17378","authors":["Xudong Pan † {\\dagger} (潘旭东)","Jiarun Dai † {\\dagger} (戴嘉润)","Yihe Fan (范一禾)","Minyuan Luo (罗铭源)","Changyi Li (李长艺)","Min Yang ∗ (杨珉)"],"aliases":["https://doi.org/10.48550/arXiv.2503.17378","https://arxiv.org/abs/2503.17378","https://arxiv.org/pdf/2503.17378"]}]}