Metraipolis › archive › dc_6d7eabfed6d5
MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments — arXiv:2610.07376
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07376
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:18:36.528Z
- SHA-256 of the archived text
8aee1bf2a973f26ae663bd13a9a9293460a438347d84316ce8407b20858142b0- Stable URL of this page
https://metraipolis.com/documento/dc_6d7eabfed6d5
How to cite
MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments — arXiv:2610.07376 — arXiv (en), https://arxiv.org/abs/2610.07376 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6d7eabfed6d5 (Metraipolis archive dc_6d7eabfed6d5, sha256 8aee1bf2a973f26ae663bd13a9a9293460a438347d84316ce8407b20858142b0)
BibTeX
@misc{dc6d7eabfed6d5,
title = {MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments — arXiv:2610.07376},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07376},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6d7eabfed6d5; sha256 8aee1bf2a973f26ae663bd13a9a9293460a438347d84316ce8407b20858142b0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07376. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM) agents increasingly operate in interactive environments, where they need to make sequential decisions through observation, action, and feedback. Although memory can help agents reuse experience, existing work designs memory in isolation, where collecting enough trajectories to populate it is expensive. Existing shared-memory approaches mitigate isolated experience by pooling episodic memories across tasks and environments. However, retrieving shared memory is challenged by the granularity, where retrieved memories can be either too specific to preserve current grounding or too coarse to support the next action. In this work, we propose MemCo, a memory-centric collaboration framework for generalizing LLM agents to unseen interactive environments. It maintains complementary local and global memory spaces, preserving environment-specific details locally while promoting transferable workflows induced from local trajectories to global memory. During online interaction, MemCo routes relevant local and global memories in terms of the agent's current state and decision phase, enabling agents to reuse the experience of other agents without blindly transferring environment-specific details. Experiments on interactive decision-making benchmarks show that MemCo improves task success and reduces redundant exploration compared with isolate-memory and shared-memory baselines. Our code is available at this https URL . 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/2610.07376 — 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 2026-10-07T11:15:24.503Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).