We build AI systems that learn from real experience — agents that remember, adapt, and act on behalf of the people who use them.

Our research focuses on continual learning and collective intelligence. The models emerge from recursive self-improvement loops on MinT, orchestrated by MindForge. The infrastructure spans model-harness co-design, long-term memory, generative interfaces, and the post-training systems required to serve all of it at scale.

How AI systems autonomously improve their own capabilities through iterative learning and experimentation.

• Mindforge — autonomous research loops that turn ideas into runnable experiments and drive continuous model improvement.
• MinT-cookbook — collection of recipes for building self-improving AI systems with MinT infrastructure.

How agents learn from interaction over time, rather than only at training.

• LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget — architecture-aware execution stack for million-token RL post-training under a fixed GPU budget.
• MinT — RL infrastructure for experiential intelligence. Abstracts compute scheduling, distributed training, rollout, and evaluation behind a unified interface.
• MinT: Managed Infrastructure for Training and Serving Millions of LLMs — scaling LoRA-based post-training and serving across frontier-scale models and million-scale adapter catalogs.

How specialized models compose and route to handle complex, multi-faceted tasks.

• Macaron-V1 — agent model family built around adaptation and collaboration. Combines a frozen base with specialized LoRA experts for conversation, agentic tasks, coding, and generative UI through a Mixture-of-LoRA architecture.
• On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters — studies parameter-efficient fine-tuning as persistent local state, and how personal models scale up, down, and out on shared foundations.
• Mixture-of-LoRA Harness — serving harness for Macaron-V1's Mixture-of-LoRA architecture, supporting specialized LoRA routing on shared base models.

How agents form, retrieve, and apply memory across sessions and over extended timelines.

• δ-mem — lightweight online memory mechanism that compresses historical information into compact state directly coupled with attention computation.
• MindClaw — experiments in personalized long-term memory through per-user LoRA fine-tuning.
• Streaming Memory Benchmark — evidence-based streaming evaluation for diagnosing memory formation, retrieval, application, latency, and token efficiency.

How agents create interfaces dynamically, rather than relying on fixed templates.

• Macaron-A2UI — generative UI model for personal agents. Generates natural language together with lightweight executable UI actions.
• UI4A — component-native generative UI harness. Lets agents generate code with imports, components, state, and actions inside enforced runtime boundaries.
• Macaron-A2UI-Bench — benchmark for controlled evaluation of generative UI capabilities in personal agents.

How we measure agent behavior in long, complex, and culturally varied contexts.

• Macaron ChatBench — evaluates conversational behavior in long and complex agent contexts, with emphasis on honesty, error awareness, and appropriate responses.
• Macaron LivingBench — long-horizon benchmark for evaluating agents across weeks of interaction, daily-life scenarios, and different cultural contexts.
• Streaming Memory Benchmark — evidence-based streaming evaluation for memory formation, retrieval, application, latency, and token efficiency.

• Macaron-V1-Venti — 748B-parameter flagship model, post-trained from GLM-5.2 with four specialized LoRA experts.
• Macaron-V1-Tall — 50B-parameter Macaron-V1 model designed for local deployment.
• Macaron Model Previews — compare the latest Macaron models side by side and test them on real-world tasks.
• MinT Cookbook — turn new research ideas into runnable MinT recipes and agent-driven experiment loops.

• Website — research, releases, and updates.
• Publications — full list of papers and technical reports.
• Contact:contact@mindlab.ltd