腾讯混元推出Hyra-1.0，一个能递归自我改进的研究智能体，在NanoChat等三项任务上均超越Recursive公开结果。
Hyra在55个数学开放问题中刷新29个历史最好结果，并设计出仅含15个可训练参数即可完成10位数加法的Transformer。
所有产物已在GitHub开源。
AI News / Products
Back to AI news
Tencent Hunyuan launches Hyra-1.0 recursive self-improving research agent
Tencent Hunyuan has launched Hyra-1.0, a research agent capable of recursively self-improving, surpassing the publicly released Recursive results in three...
Today AI Intelligence Brief
Tencent Hunyuan has launched Hyra-1.0, a research agent capable of recursively self-improving,
surpassing the publicly released Recursive results in three tasks including NanoChat. Hyra has set 29 new historical best results among 55 open mathematical problems and has designed a Transformer that can perform 10-digit addition with only 15 trainable parameters. All products have been open-sourced on GitHub.
资讯正文 · AI 整理
Intelligence Assessment
Aioga 编辑摘要
腾讯混元发布研究智能体Hyra-1.0。公开材料称，其在NanoChat等三项任务上超过Recursive公开结果，并在55个数学开放问题中刷新29项历史最好结果，相关产物已在GitHub开源。
背景分析
本次信息来自腾讯混元公众号，材料将Hyra-1.0描述为可递归自我改进的研究智能体，并以任务结果、数学开放问题表现及特定Transformer设计作为主要成果依据。
Aioga 观点
Aioga判断，Hyra-1.0的关注点在于将递归自我改进与可核验的研究产物结合。不过，现有材料未披露具体评测流程、比较条件及复现结果，暂不宜据此推导更广泛能力。
影响与后续
Aioga判断，开源产物可能为外部复核三项任务表现、29项历史最好结果及15参数Transformer提供条件。其实际研究价值仍取决于代码、数据、评测设置能否被独立复现。 值得关注GitHub开源产物中的实验配置、基线定义、结果记录与复现说明，并核对“超过Recursive公开结果”及数学问题成绩的评测口径；在独立验证前，应将相关结论限定于公开材料所述范围。
Source and Copyright
The readable text on this page was extracted from the public source and organized with attribution, publication time and the original link. Copyright remains with the original author and publisher.
Ingestion channel: Summary aggregation · Source domain: mp.weixin.qq.com
Source: 公众号：腾讯混元
Original link: Open original source
Aioga archive: Open intelligence page
Content record: summary-fallback · Updated: 2026-07-21T03:33:08.000Z
API RELAY · DEVELOPER INFRASTRUCTURE
API 中转站
统一接入主流 AI 模型 API，为开发、测试与生产环境提供稳定调用入口。
立即访问 api.w173.com
Scan to open this article