推理循环
A state where a model gets stuck in self-repetition during generation without converging to a final answer, often leading to tru
MIT CSAIL researchers introduced 'Weight-Space Programming,' a method where GPT-6 Astra directly reads and edits the neural network weights of Qwen3.5-0.8B. Without gradient descent or traditional training loops, adjusting just ~0.016% of parameters eliminated reasoning loops, boosting MATH-500 scores from 7.9% to 48.1%, offering a new paradigm for model optimization and interpretability.
MIT CSAIL researchers introduced 'Weight-Space Programming,' a paradigm where frontier LLMs like GPT-6 Astra directly read and edit neural network weights without gradients or retraining. Experiments showed that modifying just 0.016% of Qwen3.5-0.8B's weights boosted its MATH-500 accuracy from 7.9% to 48.1%, primarily by removing reasoning loops rather than adding new knowledge. This study demonstrates that LLMs can natively manipulate model parameters, offering a new path for AI self-improvement, though results await independent replication.
MIT researchers demonstrated 'Weight-Space Programming,' a new paradigm where frontier LLMs like GPT-6 Astra directly edit the weights of other AI models without training or gradients. By modifying just 0.016% of Qwen3.5-0.8B's weights to fix reasoning loops, the method boosted math accuracy from 7.9% to 48.1%, achieving nearly 6x performance improvement.