Understand this story
On November 2, 2026, Tencent Hunyuan released Hyra 2.0, the next-generation version of its Hunyuan Research Agent. According to official information, Hyra 2.0's positioning has shifted from solving problems to building reusable tools, models, and workflows to accelerate subsequent discoveries, and Tencent Hunyuan also released its views on the next stage of AutoResearch. On the same day, Phoenix Technology reported that the system's R&D focus has shifted toward having general-purpose agents participate in the development and upgrading of scientific models, research workflows, and software tools, and that it divides research work into three layers—Overall, Mission, and Worker—and designs three separate storage mechanisms: project state, agent hierarchical memory, and a shared knowledge base called Books; during project retrospectives, transferable methods can be organized into skills for use in subsequent tasks. The report also mentioned that Hyra 1.0 had previously driven open-source models to solve an open problem in additive combinatorics that had remained unresolved for more than fifty years. There are currently no further developments.
AI-generated from public reports
Latest update · Discussion
Phoenix Technology joined this discussionDevelopments
1 confirmed developments
- Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 2
Phoenix TechnologyRelated discussion
Phoenix Technology joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Phoenix Technology
Tencent Hunyuan Releases AI Research System Hyra 2.0
Tencent Hunyuan released the AI research system Hyra 2.0 on November 2, shifting its R&D focus from directly using AI to tackle scientific problems toward having general-purpose Agents participate in the development and upgrading of scientific models, research workflows, and software tools. The system splits research work into three layers—Overall, Mission, and Worker—and designs three separate storage mechanisms: project state, layered Agent memory, and a shared knowledge base called Books. During project retrospectives, transferable methods can be organized into skills for use in subsequent tasks. Previously, Hyra 1.0 drove open-source models to solve an open problem in additive combinatorics that had remained unresolved for over fifty years.
TeortaxesRelated discussion
Teortaxes joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Tencent HunyuanFirst-party
Tencent Hunyuan Releases Research Agent Hyra 2.0
Tencent Hunyuan has released Hyra 2.0, the next-generation version of the Hunyuan Research Agent, positioned to shift from solving problems to building reusable tools, models, and workflows in order to accelerate subsequent discoveries. The official team also published its views on the next stage of AutoResearch, with the link https://t.co/u2JSslKYai.
Heat trend for this story
- Current
- 28
- Period peak
- 28 Nov 2 22:00
- 24-hour change
- —
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.