RLAE uses PPO and MAPPO policies to assign per-span ensemble weights across 7B-8B LLMs; it claims up to 3.3% accuracy improvement over prior ensemble baselines but underperforms on several tested tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
RLAE: Reinforcement Learning-Assisted Ensemble for LLMs
RLAE uses PPO and MAPPO policies to assign per-span ensemble weights across 7B-8B LLMs; it claims up to 3.3% accuracy improvement over prior ensemble baselines but underperforms on several tested tasks.