Skip to main content
← Back to news

ClawLoop: self-improving agents without an external teacher model

Research
Source:Hugging Face
ClawLoop (LongCat) trains sandbox LLM agents through a self-sustaining three-phase cycle — task synthesis, SFT/RL training, rollout diagnosis — where the diagnosis feeds the next task synthesis, removing the external model that normally synthesizes tasks and trajectories. With Qwen3.6-27B it improves on SkillsBench, Claw-Eval-Live and ClawGym-Bench; the refined tasks transfer with gains even to Qwen3.5-4B and 9B.
Read original article

Related articles

Running LLM Models Locally: From First Install to First Working Model

From zero to a first answering model: what you actually need, Ollama step by step, how to pick a model for your memory, expected speeds per hardware, and the typical problems fixed.

ML agents that run locally: MLExpert and EpochGo on Ollama, zero API costs

MLExpert raises the bar to 35B and a 72.7% medal rate; EpochGo runs three AutoML agents on 16 GB at zero API cost: what works today, the math and the limits.

Llama 3 and Llama 4: Meta's open family — which model runs on your hardware

From the 3.1 8B to the 4 Scout MoE with a 10M context: the Llama family in a table, what runs on 16, 48 and 128 GB of RAM, the Community license translated for the Italian business and the choice by budget.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🦉

Qwen3.8-27B

Models

Il modello dense multimodale della generazione Qwen3.8 di Alibaba: 27,78B di parametri, input testo+immagini+video e contesto nativo di 262K token. Licenza Apache 2.0. L'attenzione ibrida (DeltaNet lineare + GQA) riduce la KV cache di circa il 75% rispetto a un transformer standard: in Q4_K_M sta su una singola GPU da 24GB.

🌱

Bonsai-2 27B

Models

27B reasoning model with ternary weights at 1.72 bits per weight, derived from Qwen3.8-27B with hybrid attention (~75% linear). In GGUF PTQ1_0 it takes 5.95 GB, retains 98.2% of the FP16 intelligence and reaches ~47 tok/s on an Apple M5 Max laptop, with a 262K-token context. Apache 2.0 license. Requires Prism ML's llama.cpp fork (ternary kernels are not in stock llama.cpp).

🧠

Qwen3 30B-A3B (MoE)

Models

Mixture-of-Experts model: 30B total params but only 3.3B active per token. Small-model speed with mid-size quality; the best speed/quality ratio in its class.

🌸

Qwen3 8B

Models

Il modello dense 8B della famiglia Qwen3: 8,19B di parametri, contesto nativo di 40K token (espandibile con YaRN) e ragionamento in modalità think/non-think attivabile per prompt. Licenza Apache 2.0. È il punto di equilibrio per l'uso locale su GPU da 8-12GB: in Q4_K_M occupa circa 5GB, lasciando spazio per contesto lungo.

Browse all resources