Rio Yokota

Evaluating Multiple LLM Generations with Validated Task Coverage

Many LLM applications are most useful when they provide several candidate outputs for comparison, validation, or combination. Predominant evaluation settings, however, still focus on individual outputs or reduce multiple samples to a single success or selected answer. This can miss whether the outputs include several g...

LLMs as Acquisition Policies for Finite-Pool Materials Optimization: A Controlled Study

Overall, open-weight LLMs show potential as acquisition policies for finite-pool materials search, although their reliability remains sensitive to the task and to how candidates and scientific context are presented.

Agent Harnesses for GPU Kernel Optimization: A Taxonomy of Failure Modes and Design Implications