GAM decouples event-level memory encoding from topic-level consolidation in LLM agents using hierarchical graphs to reduce interference and improve long-term coherence and retrieval.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.
citing papers explorer
-
GAM: Hierarchical Graph-based Agentic Memory for LLM Agents
GAM decouples event-level memory encoding from topic-level consolidation in LLM agents using hierarchical graphs to reduce interference and improve long-term coherence and retrieval.
-
Prompt Governance? On Governing Technologies Governed by Natural Language
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.