Metraipolis › archive › dc_7fc272ede02b

MemDuet: Learning Dual-Process Memory for Long-Context Reasoning — arXiv:2610.19928

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.19928
License (as archived): CC0-1.0
Archived: 2026-10-15T20:34:52.996Z
SHA-256 of the archived text: 7d73586f46fd31ad1aa17cb7582960e8653a0ee2b4957dfc1aa141049255ea0f
Stable URL of this page: https://metraipolis.com/documento/dc_7fc272ede02b

How to cite

MemDuet: Learning Dual-Process Memory for Long-Context Reasoning — arXiv:2610.19928 — arXiv (en), https://arxiv.org/abs/2610.19928 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fc272ede02b (Metraipolis archive dc_7fc272ede02b, sha256 7d73586f46fd31ad1aa17cb7582960e8653a0ee2b4957dfc1aa141049255ea0f)

BibTeX

@misc{dc7fc272ede02b,
  title = {MemDuet: Learning Dual-Process Memory for Long-Context Reasoning — arXiv:2610.19928},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19928},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fc272ede02b; sha256 7d73586f46fd31ad1aa17cb7582960e8653a0ee2b4957dfc1aa141049255ea0f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19928. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reasoning over infinitely long documents is becoming a reality with recurrent memory agents. However, increasing context length exacerbates the trade-off between reasoning performance and inference efficiency. Inspired by Kahneman's account of fast and slow thinking, we propose MemDuet, a dual-process memory framework that learns to coordinate a small language model for fast, parallel evidence selection from raw context chunks (System 1) with a large language model for memory-update verification and memory updates in document order (System 2). We train MemDuet in three stages: supervised fine-tuning of System 1 for evidence selection, Group Relative Policy Optimization (GRPO) of System 2 for verification and memory rewriting, and joint optimization of both policies to coordinate selection and updating for long-context reasoning. Experiments on diverse long-context reasoning benchmarks (RULER-HQA, LongBench v2, and 2WikiMultiHopQA) demonstrate a favorable accuracy-efficiency trade-off as context length grows. Averaged across evaluation settings on the three datasets, MemDuet achieves an end-to-end inference speedup of 9.74x and an output-token reduction of 73.91% relative to RL-MemAgent.

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/2610.19928 — 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 2026-10-15T19:36:18.233Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).