Compacting reasoning history shortens future generation and can cut agent cost
Open-weight models rewrite earlier thoughts into compact state records before tool results, without retraining.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #efficient-reasoning
Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability
Efficient reasoning fine-tuning usually reduces chain-of-thought faithfulness, while monitorability stays more robust.
Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition
Lightning Weave composes capabilities from independently post-trained models via on-policy distillation, improving Qwen3.5-4B reasoning accuracy while cutting tokens.