MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration

arXiv:2604.14889v1 Announce Type: new Abstract: While Chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning problems, as KV cache grows linearly with the number of generated tokens, CoT reasoning faces scaling issues in terms of speed and memory usage. In this work, we propose MemoSight (Memory-Foresight-based reasoning), a unified framework that integrates both context compression and multi-token prediction to mitigate the efficiency issues while maintaining CoT reasoning