AI RESEARCH
PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training
arXiv CS.AI
•
ArXi:2604.03675v1 Announce Type: new In agentic search, large language models (LLMs) are trained to perform multi-turn retrieval and reasoning for complex tasks such as multi-hop question answering (QA). However, current search-based Reinforcement Learning (RL) methods suffer from two core limitations: expensive long-horizon rollouts are under-utilized during