Updates

Insights, explorations, and progress from across Mind Lab.

Macaron-V1-Preview: 749B MoL Agent Model post-trained from GLM5.1

Macaron-V1-Preview: 749B MoL Agent Model post-trained from GLM5.1

June 7, 2026

MinT Cookbook: From Reproducible Baselines to Continuous Autoresearch

MinT Cookbook: From Reproducible Baselines to Continuous Autoresearch

May 29, 2026

Macaron-A2UI: A Model for Generative UI in Personal Agent

Macaron-A2UI: A Model for Generative UI in Personal Agent

April 30, 2026

Support GLM5 and GLM5.1 in MinT: LoRA training for DSA and MTP

Support GLM5 and GLM5.1 in MinT: LoRA training for DSA and MTP

April 23, 2026

0.03% Parameters, 100% Potential: Reflexivity of Compute Optimal Rank Scaling

0.03% Parameters, 100% Potential: Reflexivity of Compute Optimal Rank Scaling

April 20, 2026

OpenClaw Skill Security: Intent-Capability-Behavior Consistency as a New Framework

OpenClaw Skill Security: Intent-Capability-Behavior Consistency as a New Framework

April 3, 2026

Triquetra for LoRA's entangled knobs: When LoRA rank changes, how should learning rate move?

Triquetra for LoRA's entangled knobs: When LoRA rank changes, how should learning rate move?

March 24, 2026

MindClaw: Fine-Tuning OpenClaw for Personalized Long-Term Memory

MindClaw: Fine-Tuning OpenClaw for Personalized Long-Term Memory

March 16, 2026

From Context Engineering to Context Learning

From Context Engineering to Context Learning

February 28, 2026

Router Replay R3: Why It Failed and How We Fixed It

Router Replay R3: Why It Failed and How We Fixed It

January 28, 2026

Streaming Memory Benchmark: Diagnosing Memory with Evidence-Grounded Episodes

Streaming Memory Benchmark: Diagnosing Memory with Evidence-Grounded Episodes

January 24, 2026

MinT: RL Infrastructure for Experiential Intelligence

MinT: RL Infrastructure for Experiential Intelligence

January 1, 2026

From Words to Worlds: How World Models Unlock Scalable Agentic RL

From Words to Worlds: How World Models Unlock Scalable Agentic RL

December 21, 2025

Exploring Agentic Memory beyond Reasoning and Tool-Use

Exploring Agentic Memory beyond Reasoning and Tool-Use

December 3, 2025

How We Build Trillion Parameter Reasoning RL with 10% GPUs

How We Build Trillion Parameter Reasoning RL with 10% GPUs

December 2, 2025

Introducing Mind Lab: Building AI that Learns from Real Experience

Introducing Mind Lab: Building AI that Learns from Real Experience

December 1, 2025

Mind Lab © 2026 · contact@mindlab.ltd