AdaLeZO uses a non-stationary multi-armed bandit to adaptively allocate perturbation budget across layers in zeroth-order optimization and applies inverse probability weighting to reduce variance while preserving unbiased gradients, delivering 1.7x-3.0x wall-clock speedup on LLaMA and OPT models.
Survey: Multi-armed bandits meet large language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3roles
background 2polarities
unclear 2representative citing papers
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
Agent2UCB applies a dual-UCB bandit with LLM priors to select GEO rewriting tools per content item, claiming near-exhaustive visibility within about 15 iterations.
citing papers explorer
-
Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling
AdaLeZO uses a non-stationary multi-armed bandit to adaptively allocate perturbation budget across layers in zeroth-order optimization and applies inverse probability weighting to reduce variance while preserving unbiased gradients, delivering 1.7x-3.0x wall-clock speedup on LLaMA and OPT models.
-
When Do We Need LLMs? A Diagnostic for Language-Driven Bandits
Lightweight numerical bandits on text embeddings match or exceed LLM accuracy in contextual bandits at a fraction of the cost, with an embedding-based diagnostic to choose between them.
-
Agent2UCB: Agentic System for Generative Engine Optimization
Agent2UCB applies a dual-UCB bandit with LLM priors to select GEO rewriting tools per content item, claiming near-exhaustive visibility within about 15 iterations.