Dynamic Policy Induction for Adaptive Prompt Optimization: Bridging the Efficiency-Accuracy Gap via Lightweight Reinforcement Learning
Anzeige
Ähnliche Artikel
arXiv – cs.LG
•
Dual-Weighted Reinforcement Learning for Generative Preference Modeling
arXiv – cs.AI
•
Mehrere KI-Modelle lernen gemeinsam: 16,7 % mehr Genauigkeit bei Logik
arXiv – cs.LG
•
Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR
arXiv – cs.AI
•
KI lernt, Rechenaufwand für Antworten dynamisch anzupassen
arXiv – cs.AI
•
GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation
arXiv – cs.AI
•
DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains