Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Thought-Level Beam Search for Reasoning
Lijie Yang, Hongyin Luo, Jiawei Zhao +2
Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question fr…
cs.AI2026
Skim: Speculative Execution for Fast and Efficient Web Agents
Mike Wong, Kevin Hsieh, Suman Nath +1
Skim is a speculative execution framework for web agents that exploits the predictable structure of purpose-built websites. Today's web-agent expense is not intrinsic to the tasks…