2 papers
cs.CL2026
Knowledge Integration Decay in Search-Augmented Reasoning of Large Language Models
Sangwon Yu, Ik-hwan Kim, Donghun Kang +6
Modern Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks by employing search-augmented reasoning to incorporate external knowledge into long c…
cs.LG2026
Snowball: A Scalable All-to-All Ising Machine with Dual-Mode Markov Chain Monte Carlo Spin Selection and Asynchronous Spin Updates for Fast Combinatorial Optimization
Seungki Hong, Kyeongwon Jeong, Taekwang Jang
Ising machines have emerged as accelerators for combinatorial optimization. To enable practical deployment, this work aims to reduce time-to-solution by addressing three challenges…