Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
Ranking
Observed public metrics from 1 member.
Merged summary
TL;DR - HiGram is an evolving hierarchical graph memory framework for long-term LLM agents that replaces flat graph memory with a coarse-to-fine structure and rewrites memory at the level of localized evidence paths. It matters because it targets the two main pain points of agent memory — retrieval noise from accumulated history and costly unit-by-unit updates.
- Hierarchical graph memory organizes storage into upper-level nodes over fine-grained MemoryUnits, cutting irrelevant context surfaced during multi-hop retrieval.
- MicroGraph-based path-level localization builds query- and update-conditioned MicroGraphs to pinpoint the support subgraph and evidence path before any rewrite occurs.
- A coordinated rewriting step jointly revises intra-unit content and inter-unit dependencies, keeping dependency structures valid instead of requiring repeated independent unit rewrites.
- Reported gains over baselines on long-term conversational QA and conflict-aware memory benchmarks cover answer quality, token efficiency, and evidence selection under dynamic, static, and conditional conflicts.
Sources (1)
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
TL;DR - HiGram is an evolving hierarchical graph memory framework for long-term LLM agents that replaces flat graph memory with a coarse-to-fine structure and rewrites memory at the level of localized evidence paths. It matters because it targets the two main pain points of agent memory — retrieval noise from accumulated history and costly unit-by-unit updates.
- Hierarchical graph memory organizes storage into upper-level nodes over fine-grained MemoryUnits, cutting irrelevant context surfaced during multi-hop retrieval.
- MicroGraph-based path-level localization builds query- and update-conditioned MicroGraphs to pinpoint the support subgraph and evidence path before any rewrite occurs.
- A coordinated rewriting step jointly revises intra-unit content and inter-unit dependencies, keeping dependency structures valid instead of requiring repeated independent unit rewrites.
- Reported gains over baselines on long-term conversational QA and conflict-aware memory benchmarks cover answer quality, token efficiency, and evidence selection under dynamic, static, and conditional conflicts.