Tencent Ships Hyra-1.0, an Agent That Critiques and Rewrites Its Own Work
Tencent's Hyra-1.0 is a self-improving research agent built on Hy3 that autonomously iterates on solutions for AI research, science, and engineering tasks
- Hyra-1.0 launched: Tencent released the first Hunyuan Research Agent, built for recursive self-improvement on performance-driven tasks.
- How it works: The agent generates a solution, evaluates it against a verifiable metric, and iterates until it hits a target -- no human in the loop between rounds.
- Three use-case tracks: AI4AI (ML optimization), AI4Science (drug discovery, materials), and AI4Fun (game strategies, creative tasks).
- Powered by Hy3: Runs on Tencent's 295B MoE model with 21B active parameters, Apache 2.0 licensed and available on Hugging Face.
- Access: Demos live at hy.tencent.com/research/hyra; API priced at 1 yuan per million input tokens on Tencent Cloud.
- Key limitation: The iterative loop only adds value when the task has a clear, numeric evaluation signal -- open-ended tasks get no benefit.
Tencent's AI lab has shipped Hyra-1.0, the first version of the Hunyuan Research Agent. Rather than returning a one-shot answer, Hyra loops over its own outputs, critiques them, and keeps revising until it hits a performance target. The system targets tasks where quality is measurable: machine learning experiments, scientific computation, and engineering optimization.
How the loop actually works
"Recursive self-improvement" has floated around AI theory for decades, but Hyra grounds it in something concrete. The agent does not rewrite its own weights. Instead, it runs a controlled iterative cycle: generate a solution, evaluate it against a verifiable objective, identify what failed, and produce a revised attempt. The model acts as both solver and critic, and the loop terminates on a metric rather than a word count or summary.
Most research agents are optimized for information retrieval and synthesis. Hyra is built for performance-driven tasks, which means the evaluation signal drives every iteration.
Three categories of use cases
Tencent organized Hyra's demos into three buckets:
- AI4AI: Using the agent to improve AI systems themselves, including hyperparameter search, architecture tuning, and automated ML pipeline optimization. The evaluation signal is a benchmark score or validation loss.
- AI4Science: Applying AI to accelerate scientific discovery across material science, drug design, and genomic analysis. Hyra targets tasks where a correct solution can be verified against physical laws or experimental data.