Long-horizon memory systems increasingly improve how evidence is stored and retrieved, yet the generator must still reason over fragments whose cross-session relationships are implicit.
We study generation-time memory organization as a distinct design dimension and introduce GRAVITY (Generation-time Relational Anchoring Via Injected Topological MemorY), a host-independent auxiliary memory layer.
GRAVITY consolidates raw dialogue into entity profiles, temporal event traces, and cross-session topic summaries, then retrieves and injects query-relevant records through the prompt interface.
Performance Across Diverse Memory Systems
Across five heterogeneous memory systems on LongMemEval and LoCoMo, it improves every host--benchmark baseline under two distinct LLM configurations.
Controlled analyses separate gains from organizing already available evidence and from consolidating information across the full history.
Enhanced Representation on LoCoMo
Under a matched LightMem pipeline, the entity--event--topic representation reaches 83.9% on LoCoMo, 3.6% above the strongest of six alternative auxiliary representations.
These results show that generation-time structure is a portable complement to existing memory retrieval, while its interaction with host evidence depends on the benchmark and host.