Tag
This paper investigates when chain-of-thought reasoning is beneficial for LLMs, showing that early-stage entropy dynamics reliably indicate reasoning utility, and introduces EDRM, a lightweight, training-free framework that adaptively selects inference strategies to achieve significant token savings while maintaining or improving accuracy.
AVR is an adaptive visual reasoning framework that dynamically selects optimal reasoning formats to reduce token usage by 50-90% while maintaining accuracy in visual reasoning tasks. The method addresses reasoning path redundancy by decomposing visual reasoning into three cognitive functions and using FS-GRPO training to encourage efficient format selection.
This paper presents a real-time verification system for retrieval-augmented generation that processes long documents up to 32K tokens, using adaptive inference strategies to balance latency and verification coverage. It provides practical guidance for building reliable RAG systems.