bayesian optimization
- Papers
- 3
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Nov 2026
3 papers in the last two months, against 0 in the two before.
Start here
Two papers to read first, in the order they came out- 1Low-dimensional language-model steering supports more systematic black-box search
BOReFT learns a low-dimensional intervention manifold in a frozen LLM for Bayesian optimization of discrete black-box functions.
Oct 2026 - 2AI steering vectors contain distinct functional parts good for control
Task vectors can be linearly decomposed into Task Recognition and Task Learning components for interpretable control.
Nov 2026
How fast it is moving
Often studied with
agentic scaffoldingExternal supports like training curricula, tool selection, and success verifiers enable agents to handle long-horizon or out-of-distribution tasks.1 togetheraudit workflowA systematic process for verifying data integrity, model behavior, and evaluation validity through checks for errors, confounds, and hidden artifacts.1 togetherdeep researchA multi-step AI system that autonomously gathers, evaluates, and synthesizes evidence from diverse sources to produce comprehensive reports.1 togetherThe papers
Most central to this idea first, not most recent.
- Big Techcs.LG
Low-dimensional language-model steering supports more systematic black-box search
BOReFT learns a low-dimensional intervention manifold in a frozen LLM for Bayesian optimization of discrete black-box functions.
University of Massachusetts Amherst, New York University · Oct 2026
- Research Labcs.LG
AI steering vectors contain distinct functional parts good for control
Task vectors can be linearly decomposed into Task Recognition and Task Learning components for interpretable control.
Keio University, RIKEN · Nov 2026
- Big Techcs.AI
Managing research ideas helps autonomous agents search faster
AIM automates idea-driven research, beating baselines by up to 4.9% and reaching best performance 3.1x faster.
Google Cloud AI Research, University of Wisconsin-Madison · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.