Metraipolis › archive › dc_3cdc490acc7f
LeanMem: Simple and Efficient Long-Term Memory for LLM Agents — arXiv:2608.03463
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03463
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:16:21.328Z
- SHA-256 of the archived text
d3654ee1ed2e4f17f59850e979e0a2db53eaa4ab8a3d864b50a1fd4d27153af7- Stable URL of this page
https://metraipolis.com/documento/dc_3cdc490acc7f
How to cite
LeanMem: Simple and Efficient Long-Term Memory for LLM Agents — arXiv:2608.03463 — arXiv (en), https://arxiv.org/abs/2608.03463 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3cdc490acc7f (Metraipolis archive dc_3cdc490acc7f, sha256 d3654ee1ed2e4f17f59850e979e0a2db53eaa4ab8a3d864b50a1fd4d27153af7)
BibTeX
@misc{dc3cdc490acc7f,
title = {LeanMem: Simple and Efficient Long-Term Memory for LLM Agents — arXiv:2608.03463},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03463},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3cdc490acc7f; sha256 d3654ee1ed2e4f17f59850e979e0a2db53eaa4ab8a3d864b50a1fd4d27153af7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03463. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typically process heterogeneous dialogue content through a uniform summarization and retrieval pipeline, leading to either excessive token consumption or irreversible loss of fine-grained evidence. We argue that historical dialogue content should be handled differently according to its compressibility, temporal dynamics, and fidelity requirements. Based on this insight, we propose LeanMem, a lightweight long-term memory framework. LeanMem first filters out low-value content, then stores informative segments as compact profile memory, temporally structured event memory, or source-grounded record memory, depending on the nature of the information. During maintenance, only dynamically evolving event memories are selectively updated, avoiding redundant consolidation of stable profiles and immutable records. During inference, LeanMem dynamically selects memory types and allocates retrieval budgets according to query-specific evidence demands, assembling relevant evidence on demand. On LoCoMo and LongMemEval-S with GPT-4.1-mini and Qwen3-8B, LeanMem improves accuracy over the strongest memory-based baseline in every setting, by up to 15.1 points, at the lowest or near-lowest construction cost, inference tokens, and latency. The code and datasets are included in the supplementary materials. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.03463 — 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 2026-10-31T12:05:52.795Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).