Preprint
Aug 2026
Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning
Memory-Augmented Compression is proposed, a training-free framework that constructs reusable reasoning memories from historical traces and retrieves them as prefill-side scaffolds to compensate for information lost during compression.
Si-Meng Zhang, Yilong Chen, Wenyuan Zhang et al.
· 0 citations