#reinforcement learning

All articles tagged with "reinforcement learning"

MetaClaw Tries to Build AI Agents That Learn While Users Step Away

Researchers from four US universities have introduced MetaClaw, a framework designed to let AI agents learn from failed tasks and retrain during idle periods detected through user signals such as calendar activity and ke

Key Takeaways

MetaClaw derives behavioral rules from failed tasks and injects them into the prompt.
The framework also updates model weights with cloud-based LoRA fine-tuning.

DT Editorial Team·Mar 29, 2026·via the-decoder.com

NousCoder-14B Brings Fully Open-Source RL to Competitive Coding

Nous Research releases a 14-billion-parameter coding model trained with reinforcement learning in just four days, publishing the entire training stack.

Key Takeaways

NousCoder-14B achieves 67.87% on LiveCodeBench v6, a 7-point improvement over its Qwen3-14B base model through reinforcement learning
The entire training pipeline, RL environment, and benchmark suite are published for full reproducibility by any researcher

DT Editorial Team·Feb 11, 2026·3 min read·via venturebeat.com