Hyra: A simple yet effective scaffold for general discovery

Tencent introduces Hyra, a simple yet effective system for automated research and recursive self-improvement. Hyra uses a Harness with a Context Agent and Proposal Agents to explore solutions across diverse environments. It outperforms Recursive's system on NanoChat Autoresearch, NanoGPT Speedrun, and SOL-ExecBench benchmarks.

From the source
Today, we introduce Hyra: a **!!#0080e6 simple yet effective!!** system that turns intelligence and compute into tangible, practical value across !!#0080e6 richer, more diverse, high-value environments!!.
hunyuan.tencent.com

Visit source ↗hunyuan.tencent.com

Announced: 21 Jul 2026 02:00 UTC
Detected: 28 Aug 2026 12:02 UTC (+38d after)

Other stories

Google Research · 27 AugPlanetary prediction engine: Automating global models via Earth AIResearch paper

Tencent · 27 AugIntroducing Hy4 previewNew model

OpenAI · 27 AugBetter answers, broader thinking: What students gain from ChatGPT and critical-thinking trainingResearch paper

LG AI Research · 27 Aug[ACL 2026] ReSQL: A Self-Improving Text-to-SQL Framework through Retrieval-Augmented Error Reasoning

Research paper

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot in Visual Studio — August update