HiGram is a hierarchical graph memory with path-level localization and coordinated rewriting that improves long-term QA accuracy and token efficiency for LLM agents.
Proceedings of the AAAI conference on artificial intelligence , number=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
HiGram is a hierarchical graph memory with path-level localization and coordinated rewriting that improves long-term QA accuracy and token efficiency for LLM agents.