Metraipolis › archive › dc_14f9c9fbbfac

LifeMem: Enabling Lifelong Experience Reuse for LLM Agents — arXiv:2609.12655

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12655
License (as archived)
CC0-1.0
Archived
2026-10-16T03:08:24.232Z
SHA-256 of the archived text
e41b7a771c61490289598e2a6d7d87d3cf37031d8c3502a1f82ea63af2fbb485
Stable URL of this page
https://metraipolis.com/documento/dc_14f9c9fbbfac

How to cite

LifeMem: Enabling Lifelong Experience Reuse for LLM Agents — arXiv:2609.12655 — arXiv (en), https://arxiv.org/abs/2609.12655 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_14f9c9fbbfac (Metraipolis archive dc_14f9c9fbbfac, sha256 e41b7a771c61490289598e2a6d7d87d3cf37031d8c3502a1f82ea63af2fbb485)
BibTeX
@misc{dc14f9c9fbbfac,
  title = {LifeMem: Enabling Lifelong Experience Reuse for LLM Agents — arXiv:2609.12655},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12655},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_14f9c9fbbfac; sha256 e41b7a771c61490289598e2a6d7d87d3cf37031d8c3502a1f82ea63af2fbb485},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12655. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model agents are expected to continuously adapt to new tasks and environments over their lifetime by reusing past experience. However, existing memory-based agents struggle to transfer reusable experience across environments and suffer from catastrophic forgetting as experience accumulated. To address these challenges, we propose LifeMem, a lifelong learning framework that enables agents to transfer knowledge across multiple environments. During learning, LifeMem clusters accumulated interaction trajectories based on underlying workflows to extract reusable skills. When solving a new task at inference time, the agent recalls relevant skills and trajectories to guide actions. To validate our method, we conduct experiments across 10 environments and over 13k tasks with 2k newly annotated interaction trajectories. Results show that LifeMem enables effective experience reuse in lifelong learning, achieving both reduced forgetting on learned tasks and superior cross-task transfer. Further analysis reveals that task streaming impacts learning, while consolidating structurally similar trajectories within memory boosts performance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.12655 — 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 2026-10-16T03:02:47.546Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).