Metraipolis › archive › dc_44e390daec2d

Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought — arXiv:2610.30755

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30755
License (as archived)
CC0-1.0
Archived
2026-10-25T21:34:35.696Z
SHA-256 of the archived text
3ec263727756fbefea3a2ac95f27b988a8ad4540df92312baff22759b1f9c87a
Stable URL of this page
https://metraipolis.com/documento/dc_44e390daec2d

How to cite

Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought — arXiv:2610.30755 — arXiv (en), https://arxiv.org/abs/2610.30755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44e390daec2d (Metraipolis archive dc_44e390daec2d, sha256 3ec263727756fbefea3a2ac95f27b988a8ad4540df92312baff22759b1f9c87a)
BibTeX
@misc{dc44e390daec2d,
  title = {Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought — arXiv:2610.30755},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30755},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44e390daec2d; sha256 3ec263727756fbefea3a2ac95f27b988a8ad4540df92312baff22759b1f9c87a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other complex operations. Is this complexity always necessary? We study Raw-RAG, a naive RAG baseline using dense retrieval and reranking over raw history to supply evidence to a reader LLM. Across LoCoMo, LongMemEval, MEME, and MemoryAgentBench, Raw-RAG ranks first among the compared memory systems in six of seven benchmark-model settings, outperforming the strongest compared agentic memory system by 0.13-5.53 points. We investigate why raw-history retrieval remains competitive. Evidence analysis shows that its higher coverage of necessary evidence can offset lower utilization. Useful evidence includes both answer values and the relations and dependency paths needed to derive them. Even complete access to transformed memory stores leaves an accuracy gap relative to raw evidence, highlighting the importance of preserving raw information. These findings challenge the necessity of complex agentic memory for the evaluated conversation tasks and establish naive RAG as an essential baseline.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.30755 — 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 2026-10-25T21:25:18.109Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).