Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
- Published
- Source
- arXiv
- Paper number
- 861
- Field
- Machine Learning
- arXiv ID
- 2608.09819
Key points
- The system uses a Mixture-of-LoRA structure that keeps the base model frozen and selects expert adapters for chat, agent, coding, or GenUI on each turn.
- It proposes a framework for continual learning after deployment through joint model and harness design plus a recursive self-improvement loop.
- It releases Venti, a 744B model based on GLM-5.2, and Tall, a 50B model based on Qwen3.6.
- It also develops UI4A, a component-native GenUI harness, and MindForge, an agent RL framework.
- It shows competitive performance with frontier models on Personal Intelligence, GenUI, and general capability benchmarks.
Paper links
External research summaries. These are not HDATF publications or measured product results.