Metraipolis › archive › dc_f87db5089770
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents — arXiv:2610.06830
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06830
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:54.941Z
- SHA-256 of the archived text
bb588467f7eeb043882badebfb040efe476562352cf630fc6eda1b63cb3c7b29- Stable URL of this page
https://metraipolis.com/documento/dc_f87db5089770
How to cite
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents — arXiv:2610.06830 — arXiv, https://arxiv.org/abs/2610.06830 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f87db5089770 (Metraipolis archive dc_f87db5089770, sha256 bb588467f7eeb043882badebfb040efe476562352cf630fc6eda1b63cb3c7b29)
BibTeX
@misc{dcf87db5089770,
title = {MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents — arXiv:2610.06830},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06830},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f87db5089770; sha256 bb588467f7eeb043882badebfb040efe476562352cf630fc6eda1b63cb3c7b29},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06830. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory in a query-agnostic manner, which can incur unnecessary preprocessing cost and discard details that later prove essential. Recent studies have begun shifting memory processing toward runtime adaptation, but typically specialize in particular operations or fixed processing schemes, leaving flexible control over performance, cost, and latency largely underexplored. To address this challenge, we present \textbf{MemPilot}, a flexible framework that orchestrates on-demand memory curation under different performance--cost--latency preferences. Specifically, we optimize a multi-step LLM policy via reinforcement learning to iteratively choose between retrieving from query-agnostic memory and delegating query-specific curation of raw multimodal history to heterogeneous LLMs and VLMs. The policy jointly controls evidence amount, curation instructions, model selection, and visual access, enabling fine-grained allocation of runtime computation. To optimize this policy under competing objectives, we adapt objective-wise advantage decoupling by separately estimating each objective's advantage before aggregation. Moreover, we introduce prefix-based marginal utility estimation for fine-grained credit assignment across multi-step rollouts. Experiments on five multimodal agent-memory benchmarks demonstrate favorable performance--cost--latency trade-offs across optimization preferences, with preference sweeps yielding broader frontiers than existing trade-off-aware baselines.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.06830 — 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 2026-10-06T05:24:06.198Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).