AGENTIC R AG-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
Not assessedPlan blockedFindingclaim-component-ablation
The paper reports that removing memory actions, rollout rejection, or both lowers average F1, and that removing both retrieval and memory rewards gives the lowest ablation average.
Source: paper-fixed:page 8, Table 2
Reported and observed measurements
average F1
m-ablation-full
Reported 33.55 percentage_points
Observed — percentage_points
average F1
m-ablation-no-rewards
Reported 19.94 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.