Metraipolis › archive › dc_e1280a451ee2
Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents — arXiv:2610.11920
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11920
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:13:23.190Z
- SHA-256 of the archived text
3b48da85c029fcbe2824f4e450d4d4d9665449c55018ff8421eff9d52b2ff990- Stable URL of this page
https://metraipolis.com/documento/dc_e1280a451ee2
How to cite
Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents — arXiv:2610.11920 — arXiv (en), https://arxiv.org/abs/2610.11920 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1280a451ee2 (Metraipolis archive dc_e1280a451ee2, sha256 3b48da85c029fcbe2824f4e450d4d4d9665449c55018ff8421eff9d52b2ff990)
BibTeX
@misc{dce1280a451ee2,
title = {Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents — arXiv:2610.11920},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11920},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1280a451ee2; sha256 3b48da85c029fcbe2824f4e450d4d4d9665449c55018ff8421eff9d52b2ff990},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11920. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
For persistent and personalized conversational agents, memory systems can enable them to remember, update, and reason over long histories by storing past interactions and retrieving relevant information. Existing memory systems typically follow two paradigms: flat-structured memory and graph-based memory. The former is lightweight but leaves event relations and state updates implicit, while the latter explicitly models memory structure but incurs additional construction cost and introduces irrelevant relations over long histories. To address these limitations, we propose QGMem, a novel memory construction and activation framework motivated by human memory, in which experience is organized into events and query-relevant events are modeled by graph as working memory. QGMem converts long dialogue histories into event-indexed atomic memory units that preserve individual experiences and consolidates related units into dynamic memory traces that retain state trajectories and current states. When a query arrives, hybrid memory retrieval gathers complementary candidate memories, and query-aware reranking activates the most relevant units as a compact working memory. To expose relational dependencies in the working memory and support conflict-aware reasoning, QGMem organizes the working memory as a local graph, which is then encoded as a graph token and provided to the LLM together with the textual working memory to improve evidence utilization during answer generation. Experiments across six benchmarks validate the framework and show consistent gains in retrieval, multi-hop evidence composition, conflict resolution, and ultra-long dialogue reasoning with compact contexts and moderate inference cost. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.11920 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T05:47:15.306Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).