Metraipolis › archive › dc_64d2dbbf93b5
UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memory — arXiv:2608.30508
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30508
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:07:36.882Z
- SHA-256 of the archived text
5e92aead13b2f250fd646472a8d8bf9d6adc19a6641380b8c5bcb95dffb51eb8- Stable URL of this page
https://metraipolis.com/documento/dc_64d2dbbf93b5
How to cite
UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memory — arXiv:2608.30508 — arXiv (en), https://arxiv.org/abs/2608.30508 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_64d2dbbf93b5 (Metraipolis archive dc_64d2dbbf93b5, sha256 5e92aead13b2f250fd646472a8d8bf9d6adc19a6641380b8c5bcb95dffb51eb8)
BibTeX
@misc{dc64d2dbbf93b5,
title = {UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memory — arXiv:2608.30508},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30508},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_64d2dbbf93b5; sha256 5e92aead13b2f250fd646472a8d8bf9d6adc19a6641380b8c5bcb95dffb51eb8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30508. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-term memory is increasingly important for conversational agents, yet existing benchmarks primarily measure memory through pointwise factual recall: whether a system can recover isolated facts or event-level details from prior interactions. Real-world memory use, however, often requires a more demanding capability: integrating distributed, implicit, and noisy evidence across extended interaction histories into coherent, task-oriented outputs. We call this capability memory utilization. Here, we introduce UtilMem, a diagnostic benchmark comprising 1,717 instances across five domains, designed to evaluate four underexplored aspects of memory utilization: reasoning over dense histories, identifying implicitly relevant memories, synthesizing distributed evidence into summaries, analyses, or plans, and resisting interference from semantically similar distractors. Evaluating a diverse set of retrieval-based and memory-augmented systems, we find that strong performance on conventional factual-memory benchmarks does not reliably translate into effective memory utilization. Moreover, retrieval alone is insufficient: even when relevant evidence is successfully recovered, systems frequently fail to integrate information across sessions or to distinguish useful evidence from plausible distractors. These findings expose a substantial gap between accessing stored information and using it effectively, and suggest that progress in long-term conversational memory will require architectures that explicitly support evidence integration and robustness to retrieval interference. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.30508 — 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 2026-10-17T07:47:52.826Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).