CiteArk 上的公开研究仓库，按热度、更新时间、具有支持性 Assessment 的结论和社区求复现排序。
学科 多智能体系统 · 1 个仓库
AGENTIC R AG-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
The paper presents AGENTIC R AG-R1, a reinforcement-learning framework for retrieval-augmented multi-step reasoning. It combines fine-grained actions, stack memory with push, pop, revision, and summarization, hierarchical outcome and process rewards, and information-aware rollout rejection. Experiments report comparisons, ablations, step-budget scaling, model-size effects, timing, and downstream agent evaluations.
