🛰️ Daily AI Frontier
‹ back to 2026-09-02

Bandits in Prod: Hyperparameter Optimization at Inference Time

Research LLM Agents

Ranking

Overall 81
Content 100
Popularity 37

Observed public metrics from 1 member.

Merged summary

TL;DR - This paper formulates inference-time configuration tuning on live, noisy requests as Online Hyperparameter Optimization and introduces IMABO, an infinitely many-armed bandit framework. It enables production systems, including LLM agents, to optimize choices without representative validation data.

  • IMABO separates selecting previously sampled configurations via a bandit policy from proposing new configurations via an interchangeable oracle.
  • Its IMOSS policy grows the active configuration set as (t^\beta) and provides an expected cumulative quantile-regret bound of (O(p_\rho^{-1/\beta} + T^{(1+\beta)/2})).
  • Tree-structured Parzen Estimation, incumbent mutation, and a pretrained tabular foundation model all improve over uniform-random configuration proposals.
  • IMABO achieves the lowest cumulative regret across the evaluated settings, spanning classical ML tuning and LLM-agent configuration.

Sources (1)

Bandits in Prod: Hyperparameter Optimization at Inference Time

arXiv cs.LG Louis Abraham, Tuan-Anh Nguyen, Nicolas Devatine 2026-09-01 arXiv:2609.01335
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-21 14:26:39.158692 UTC

TL;DR - This paper formulates inference-time configuration tuning on live, noisy requests as Online Hyperparameter Optimization and introduces IMABO, an infinitely many-armed bandit framework. It enables production systems, including LLM agents, to optimize choices without representative validation data.

  • IMABO separates selecting previously sampled configurations via a bandit policy from proposing new configurations via an interchangeable oracle.
  • Its IMOSS policy grows the active configuration set as (t^\beta) and provides an expected cumulative quantile-regret bound of (O(p_\rho^{-1/\beta} + T^{(1+\beta)/2})).
  • Tree-structured Parzen Estimation, incumbent mutation, and a pretrained tabular foundation model all improve over uniform-random configuration proposals.
  • IMABO achieves the lowest cumulative regret across the evaluated settings, spanning classical ML tuning and LLM-agent configuration.
item →