GCAgent
GCAgent: Graph-Centric Episodic Memory for Long Video Agents
Jeong Hun Yeo, Sangyun Chung, Sungjune Park, Dae Hoe Kim, Jinyoung Moon, Yong Man Ro · 2025-11-15
- Management
- T2 Dynamic Memory
- Memory changes during deployment through a stable management policy.
- Representation
- Cross-represented explicit
How experience becomes memory
Each path is one memory component, traced from what is stored to how it is found again.
schematic episodic memory
- Represented asSpatial, temporal & cross-modal structured memoryCross-represented explicit
- Stored inGraph / relational store
- Retrieved byStructure traversal, Planner / tool-assisted retrieval
- Source evidenceSource linked & recoverable
Schematic and narrative episodic memories encode entities, events, and causal-temporal relations.Full-paper method / memory representation and retrieval · PDF p. 2 · Figure 1
narrative episode summaries
- Represented asPerception-to-text records & summariesCross-represented explicit
- Stored inHierarchical multi-tier store
- Retrieved bySimilarity search
- Source evidenceSource linked & recoverable
Narrative memory summarizes episodes for later perception-action-reflection reasoning.Full-paper method / memory representation and retrieval · PDF p. 2 · Figure 1
How memory changes (T2 operations)
Consolidation · Episodic / hierarchical summarization
Trajectory observations are consolidated into narrative episodes. For GCAgent, this specifically supports episodic or hierarchical summarization of schematic episodic memory.
Update · Prompted LLM/VLM record update
During operation, GCAgent applies LLM-mediated memory editing to schematic episodic memory; the memory state changes while the governing update policy remains fixed.
Related systems
- Mobile-Agent-ET2 · GUI & computer use
- GeoForgeT3 · Image
- IMPACT-CYCLET2 · Video & streaming
- MobiMemT3 · GUI & computer use
- One Sentence One DramaT2 · Video & streaming
- Video-EMT2 · Video & streaming