Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems
Taro Yano, Yoichi Ishibashi, Masafumi Oyamada
Best-of-N sampling is a simple inference-time scaling strategy for large language models, yet its behavior under incomplete reward models remains poorly understood. We study Best-o…
cs.SE2026
Effective Harness Engineering for Algorithm Discovery with Coding Agents
Yoichi Ishibashi, Taro Yano, Masafumi Oyamada
AlphaEvolve and FunSearch have demonstrated the potential of combining large language models (LLMs) with evolutionary search for automated algorithm discovery. However, discovery s…