AGENTIC R AG-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
Not assessedPlan blockedFindingclaim-efficiency-generalization
The paper reports lower average inference time than TC-RAG and downstream results on MedQA, DeepResearch Bench, ALFWorld, and WebShop.
Source: paper-supplement:pages 20 and 26-27, Tables 8 and 13-15
Reported and observed measurements
average inference time
m-time-ours
Reported 10.15 seconds
Observed — seconds
average inference time
m-time-tcrag
Reported 11.86 seconds
Observed — seconds
answer accuracy
m-medqa-answer
Reported 87 percentage_points
Observed — percentage_points
Assessments (0)
No immutable Assessment has been published for this Claim yet.
Runs (0)
No execution has been linked to this Claim yet.