Supervised fine-tuning of pretrained LLMs on offline trajectories yields better few-shot sequential decision-making than in-context-only baselines, with a theoretical suboptimality bound derived for linear MDPs by interpreting attention as Q-function estimation.
Optimal dynamic treatment regimes.Journal of the Royal Statistical Society Series B: Statistical Methodology, 65(2):331–355
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning
Supervised fine-tuning of pretrained LLMs on offline trajectories yields better few-shot sequential decision-making than in-context-only baselines, with a theoretical suboptimality bound derived for linear MDPs by interpreting attention as Q-function estimation.