Metraipolis › archive › dc_ec62338d9abb
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations — arXiv:2609.09664
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09664
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:24:29.011Z
- SHA-256 of the archived text
eec18a61534be25ef2e549cfa201065ff5b085320811c5b089f17b64a23f0c88- Stable URL of this page
https://metraipolis.com/documento/dc_ec62338d9abb
How to cite
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations — arXiv:2609.09664 — arXiv (en), https://arxiv.org/abs/2609.09664 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec62338d9abb (Metraipolis archive dc_ec62338d9abb, sha256 eec18a61534be25ef2e549cfa201065ff5b085320811c5b089f17b64a23f0c88)
BibTeX
@misc{dcec62338d9abb,
title = {PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations — arXiv:2609.09664},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09664},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec62338d9abb; sha256 eec18a61534be25ef2e549cfa201065ff5b085320811c5b089f17b64a23f0c88},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09664. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversations grow longer, relying on full interaction histories becomes increasingly inefficient and unreliable: long contexts introduce substantial computational overhead, making it difficult for models to consistently identify and utilize the most relevant information for the current request. These challenges have motivated memory systems that structure and retrieve user-specific information. In realistic interactions, users often seek practical guidance such as recommendations, planning, and decision support. Unlike factual recall tasks, personalized guidance requires models to integrate information across multiple past conversations and reason about changing user preferences and experiences. However, existing conversational memory evaluations mainly focus on retrieval and factual recall. To study this challenge, we introduce PRAGMA, a benchmark for evaluating personalized guidance in long-term conversations. PRGAMA contains curated longitudinal conversation histories, evidence annotations, and guidance scenarios grounded in evolving user contexts and incorrect user assumptions. Experiments across retrieval systems, memory systems, and long-context models reveal that current systems struggle both to recover the appropriate conversational evidence and to effectively use it for personalized guidance. Our results highlight the need for memory architectures that support robust conversational retrieval and memory-grounded reasoning beyond evidence recall. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.09664 — 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 2026-10-16T07:00:16.204Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).