Author

Kenji Kawaguchi

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning

Evaluator-guided reasoning presents a local control problem at every step: trust the current answer, return a fallback, or spend more inference. We formulate this choice as a compute-aware three-action controller, scoring terminal actions by predicted answer success and expansion by a rollout-based continuation-success...

Wei-Da Liang, Kenji Kawaguchi · 0 citations

#machine learning Preprint Oct 2026

Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback

Language model systems repeatedly make test-time decisions by comparing similarity: they retrieve exemplars, rank candidates, and revise responses. Yet similarity is not unique: lexical, semantic, structural, and stylistic resemblance can point to different candidates, and the task-aligned notion can change across inst...

Wei-Da Liang, Kenji Kawaguchi · 0 citations