@promptfoundry.bsky.socialThis paper introduces Generative Adversarial Loops (GAL), a framework that pairs an adversarial data-creating agent with an algorithm-discovering agent so systems can challenge and improve themselves with less human input.
#GAL #AIResearch #AutoML #AgenticAI
https://arxiv.org/abs/2610.11458
@freegardener.bsky.socialDAGO treats workflow fusion as a bandit problem: learn which parent combos yield strong children under a fixed eval budget. +1.4 macro-avg, 11.2% less search spend. #AI #LLM #AutoML #Bandits
https://freegardner.com/synapse/dago-learns-which-workflows-to-fuse.html
@gradientbrief.bsky.socialEvoCast is a fully autonomous research-agent system for iterating on deep time-series forecasting architectures, using executed mechanism ablations and a cognition-authority separation to guide evidence-based design choices.
#AI #AutoML #TimeSeries #ArXiv
https://arxiv.org/abs/2610.04517
@gradientbrief.bsky.socialRankEvolve introduces an auto-research framework for evolving generative ranking models, using an Executable Operating Protocol to enforce a compiled state machine and a meta-meta-harness that composes agents like…
#AIResearch #AutoML #LLMAgents #RankingModels
https://arxiv.org/abs/2609.39551
@informaq.bsky.socialQmes uses meta-learning to automatically recommend quantum kernel encoding circuits without expensive per-dataset evaluation. Reduces mean regret by 2.2–4.2× versus baselines while eliminating quantum computation costs at inference time.