Laguna M.1 Collection Our most capable model to date, designed for long-horizon work. Apache 2.0. • 4 items • Updated 3 days ago • 18
HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness Paper • 2606.12882 • Published 21 days ago • 13
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills Paper • 2603.25158 • Published Mar 26 • 56
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World Paper • 2605.26086 • Published May 25 • 24
Prompting Policies for Multi-step Reasoning and Tool-Use in Black-box LLMs with Iterative Distillation of Experience Paper • 2605.14443 • Published May 14 • 1
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy Paper • 2604.21764 • Published Apr 23 • 2
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning Paper • 2605.28742 • Published May 27 • 4