An RL agent learns domain re-weighting policies from evaluation feedback to improve balanced performance in continual pre-training of LLMs across source and target domains.
arXiv e-prints (2024), arXiv–2407
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training
An RL agent learns domain re-weighting policies from evaluation feedback to improve balanced performance in continual pre-training of LLMs across source and target domains.