A 2x2 ablation shows repeated shared access enables grokking while addressable memory (not recurrence) enables edit propagation in transformer variants on synthetic KG QA.
arXiv preprint arXiv:2502.06049 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
citing papers explorer
-
Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory
A 2x2 ablation shows repeated shared access enables grokking while addressable memory (not recurrence) enables edit propagation in transformer variants on synthetic KG QA.
-
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
- The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes