Metraipolis › archive › dc_a67d7b6aa0fc

RuleMem: Active Rule Memory for Long-Term Conversational Agents — arXiv:2609.03915

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.03915
License (as archived): CC0-1.0
Archived: 2026-10-17T01:40:48.144Z
SHA-256 of the archived text: fef3fe3979b414e5abe52049db37bc98dfaace57ee9f13e6ed1ac1e6be1c3063
Stable URL of this page: https://metraipolis.com/documento/dc_a67d7b6aa0fc

How to cite

RuleMem: Active Rule Memory for Long-Term Conversational Agents — arXiv:2609.03915 — arXiv (en), https://arxiv.org/abs/2609.03915 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a67d7b6aa0fc (Metraipolis archive dc_a67d7b6aa0fc, sha256 fef3fe3979b414e5abe52049db37bc98dfaace57ee9f13e6ed1ac1e6be1c3063)

BibTeX

@misc{dca67d7b6aa0fc,
  title = {RuleMem: Active Rule Memory for Long-Term Conversational Agents — arXiv:2609.03915},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03915},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a67d7b6aa0fc; sha256 fef3fe3979b414e5abe52049db37bc98dfaace57ee9f13e6ed1ac1e6be1c3063},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03915. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechanisms primarily treat past information as \textit{passively} stored facts, leading to semantic gaps and unreliable reasoning. To address this limitation, we propose RuleMem, a rule-based memory framework that induces reusable logical rules from historical interactions to \textit{actively} guide both evidence retrieval and reasoning. Specifically, RuleMem constructs natural-language Horn clauses from conversations and validates them via a Rule Perplexity Consistency (RPC) mechanism. These induced rules enable the retrieval of semantically distant evidence while providing an explicit logical structure for answer generation. We conducted a comprehensive evaluation of RuleMem on two long-term conversational benchmarks, LoCoMo and LongMemEval_s*. In a rigorous comparison against 14 baselines on LoCoMo, RuleMem achieved the highest accuracy, exceeding the baseline average by 27.47 points (a 54.3% relative improvement).

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.03915 — 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 2026-10-17T01:11:43.563Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).