Research repositories

Requests Import

Public research repositories on CiteArk, sorted by activity, update time, claims with supporting Assessments, and community reproduction requests.

Subject Multiagent Systems · 1 repository

Filters

Subjects

Computer Science

Statistics

Verification

Updated

First published

Status

AGENTIC R AG-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing

0/4Updated —

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.

00arXiv 2026Artificial IntelligenceMachine Learning (cs.LG)Multiagent Systems—