{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"self-replication","title":"Frontier AI systems have surpassed the self-replicating red line","aliases":["Self-Replication"],"authors":["Xudong Pan (潘旭东)","Jiarun Dai (戴嘉润)","Yihe Fan (范一禾)","Min Yang (杨珉)"],"primaryFunction":"discovery","secondaryFunctions":[{"function":"evaluation","rationale":{"en":"The work defines or applies an explicit evaluation setting in addition to its main monitoring or control contribution.","zh":"该工作除主要监测或控制贡献外，还定义或应用了明确评测设置。"}}],"kind":"study","sourceId":"self-replication","attributionSourceId":"self-replication","originalUrl":"https://arxiv.org/html/2412.12140v1","publicationDate":"2024-12-09","updatedOn":"2026-10-25","areas":["autonomy"],"scopeNote":{"en":"Primary dimension follows the source’s measured construct. Metric-level interpretations may differ.","zh":"主维度依据来源实际测量的构念；具体指标可能属于其他维度。"},"protocolIds":["self-replication"],"contributions":[{"organizationId":"fudan","role":"research","sourceId":"self-replication","locator":"Author affiliations on the original paper title page"}],"summary":{"en":"Whether instructed systems create a separate live copy in controlled trials.","zh":"受指令系统能否在受控试验中建立独立存活副本。"},"note":{"question":{"en":"Trial outcomes for two model-driven systems.","zh":"两个模型驱动系统的试验结果。"},"method":{"en":"Prompted model-driven system in a controlled environment","zh":"受控环境中按指令行动的模型系统"},"finding":{"en":"Whether instructed systems create a separate live copy in controlled trials.","zh":"受指令系统能否在受控试验中建立独立存活副本。"},"supports":null,"limits":{"en":"The supplied environment, explicit instruction and scaffold bound the finding.","zh":"所提供环境、明确指令与脚手架限定了结论。"},"connections":null},"resources":[],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"Existing source-specific draft sections are retained with limited review status. A complete methods, findings and limitations check remains pending; generic sections were omitted.","zh":"已有的来源相关草稿章节予以保留，审核状态为有限核查。完整的方法、发现与限制核查仍待完成；通用套话章节已省略。"},"noteSourceLocator":"Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification.","tags":[]},"reading":{"id":"self-replication","title":"Frontier AI systems have surpassed the self-replicating red line","en":{"takeaway":"A controlled scaffold enabled end-to-end copying; the result concerns an instructed system with access to resources.","question":"Can the tested LLM-plus-scaffold create a separate functioning copy without intermediate human assistance?","design":"The authors combine two open-weight models with an action-feedback scaffold, repeat the copying task, and inspect traces; shutdown and chain variants are additional demonstrations.","findings":["Both tested systems produced successful copies in the supplied environment.","Trace analysis associates early environment exploration with success; this is observational, not a randomized test of exploration."],"interpretation":"NUWA interpretation: copying capability under favorable access is distinct from spontaneous replication intent or a self-sustaining population.","limits":"Two models and a specific scaffold do not represent deployment prevalence. The authors’ broad societal extrapolation exceeds the directly observed copying task.","connections":["NUWA connection: the extended replication study broadens the model set; RepliBench decomposes prerequisites rather than measuring this same endpoint."],"decisionRelevance":"NUWA recommendation: retain access, scaffold, instruction and endpoint definitions before using this work in a replication-risk threshold."},"zh":{"takeaway":"受控脚手架中出现了端到端复制；结论针对获得任务指令和资源访问的系统。","question":"接受复制指令的模型与脚手架，能否在没有中途人工帮助时建立独立运行副本？","design":"作者将两个开源权重模型接入行动与反馈循环，重复复制任务并检查轨迹；另以关机和链式场景展示能力。","findings":["两个系统在所提供环境中均有成功副本。","轨迹分析发现早期探索与成功相关，但不是随机干预探索行为的因果实验。"],"interpretation":"NUWA 解读：有利权限下的复制能力不同于自发复制意图，也不同于自我维持的群体。","limits":"两个模型与特定脚手架不能代表部署发生率；作者的宏观风险推论超出直接观察的复制任务。","connections":["NUWA 关联：扩展研究扩大模型集合；RepliBench 分解前置能力，终点与本研究不同。"],"decisionRelevance":"NUWA 建议：用于复制风险阈值前，应保留访问权限、脚手架、任务指令和成功终点。"},"sourceRefs":[{"sourceId":"self-replication","url":"https://arxiv.org/html/2412.12140v1","locator":"2 Experiment designs","version":"Selected original resource https://arxiv.org/html/2412.12140v1; sha256:8ae65ad64820f261fcf3f5bc09bfa4e56c5117fc85d487bccff555572a969903; archived source capture; exact capture time not independently established","artifactSha256":"8ae65ad64820f261fcf3f5bc09bfa4e56c5117fc85d487bccff555572a969903"},{"sourceId":"self-replication","url":"https://arxiv.org/html/2412.12140v1","locator":"3.1 Summary of results","version":"Selected original resource https://arxiv.org/html/2412.12140v1; sha256:8ae65ad64820f261fcf3f5bc09bfa4e56c5117fc85d487bccff555572a969903; archived source capture; exact capture time not independently established","artifactSha256":"8ae65ad64820f261fcf3f5bc09bfa4e56c5117fc85d487bccff555572a969903"},{"sourceId":"self-replication","url":"https://arxiv.org/html/2412.12140v1","locator":"3.4 Analyzing key factors behind successful self-replication","version":"Selected original resource https://arxiv.org/html/2412.12140v1; sha256:8ae65ad64820f261fcf3f5bc09bfa4e56c5117fc85d487bccff555572a969903; archived source capture; exact capture time not independently established","artifactSha256":"8ae65ad64820f261fcf3f5bc09bfa4e56c5117fc85d487bccff555572a969903"},{"sourceId":"self-replication","url":"https://arxiv.org/html/2412.12140v1","locator":"4 Discussion","version":"Selected original resource https://arxiv.org/html/2412.12140v1; sha256:8ae65ad64820f261fcf3f5bc09bfa4e56c5117fc85d487bccff555572a969903; archived source capture; exact capture time not independently established","artifactSha256":"8ae65ad64820f261fcf3f5bc09bfa4e56c5117fc85d487bccff555572a969903"}],"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":"10f3adeb256b2855aa246406d0dc3cc2532c206716f78f77db359be191c5c601"}},"sources":[{"id":"self-replication","title":"Frontier AI systems have surpassed the self-replicating red line","url":"https://arxiv.org/html/2412.12140v1","version":"arXiv:2412.12140v1","publicationDate":"2024-12-09","datePrecision":"day","type":"controlled-study","verifiedOn":"2026-10-24","documentId":"arxiv:2412.12140","authors":["Xudong Pan (潘旭东)","Jiarun Dai (戴嘉润)","Yihe Fan (范一禾)","Min Yang (杨珉)"],"aliases":["https://doi.org/10.48550/arXiv.2412.12140","https://arxiv.org/abs/2412.12140","https://arxiv.org/pdf/2412.12140"]}]}