ASAP integrates an LLM agent over a pool of HPO tools and adds system-level optimizations (prefix-stable prompts, speculation parallelism, Self-Tuner) to improve end-to-end wall-clock performance on diverse HPO tasks.
Hpobench: A collection of reproducible multi-fidelity benchmark problems for hpo.arXiv preprint arXiv:2109.06716
4 Pith papers cite this work, alongside 9 external citations. Polarity classification is still indexing.
4
Pith papers citing it
9
external citations · external index
years
2026 4verdicts
UNVERDICTED 4representative citing papers
RAISE is a standardized benchmark for RAG hyperparameter optimization that evaluates 13 search algorithms across seven datasets and finds performance is highly task-dependent.
The Portable Regime Score PRS=(B/|A|)(1-rho) captures and predicts acquisition function performance reversals in transfer Bayesian optimization, enabling a RegimePlanner that adapts and beats fixed baselines.
BayMOTH unifies meta-Bayesian optimization with a usefulness-based fallback to lookahead, demonstrating competitive results on function optimization tasks even under low task relatedness.
citing papers explorer
-
ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments
ASAP integrates an LLM agent over a pool of HPO tools and adds system-level optimizations (prefix-stable prompts, speculation parallelism, Self-Tuner) to improve end-to-end wall-clock performance on diverse HPO tasks.
-
RAISE: RAG Design as an Architecture Search Problem
RAISE is a standardized benchmark for RAG hyperparameter optimization that evaluates 13 search algorithms across seven datasets and finds performance is highly task-dependent.
-
Regime-Conditioned Evaluation in Multi-Context Bayesian Optimization
The Portable Regime Score PRS=(B/|A|)(1-rho) captures and predicts acquisition function performance reversals in transfer Bayesian optimization, enabling a RegimePlanner that adapts and beats fixed baselines.
-
BayMOTH: Bayesian optiMizatiOn with meTa-lookahead -- a simple approacH
BayMOTH unifies meta-Bayesian optimization with a usefulness-based fallback to lookahead, demonstrating competitive results on function optimization tasks even under low task relatedness.