发表机构
The University of British Columbia; Vector Institute; NVIDIA（不列颠哥伦比亚大学; 向量研究所; 英伟达）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MemCo提出内存中心协作框架，通过互补的局部与全局内存空间及按状态和决策阶段路由记忆，提升LLM智能体在未见环境中的任务成功率并减少冗余探索。
AI 中文摘要
大型语言模型（LLM）智能体日益在交互式环境中运行，需要在此类环境中通过观察、行动和反馈进行顺序决策。尽管内存可以帮助智能体复用经验，但现有工作孤立地设计内存，其中收集足够轨迹以填充内存成本高昂。现有的共享内存方法通过跨任务和环境汇集情景记忆来缓解孤立经验问题。然而，共享内存的检索面临粒度挑战，检索到的记忆可能过于具体而无法保持当前情境，或过于粗糙而无法支持下一步行动。在本工作中，我们提出MemCo，一种用于将LLM智能体泛化到未见交互环境的内存中心协作框架。它维护互补的局部和全局内存空间，在局部保留环境特定细节，同时促进从局部轨迹归纳出的可迁移工作流提升至全局内存。在在线交互期间，MemCo根据智能体的当前状态和决策阶段路由相关的局部和全局记忆，使智能体能够复用其他智能体的经验，而不会盲目迁移环境特定细节。在交互式决策基准上的实验表明，与孤立内存和共享内存基线相比，MemCo提高了任务成功率并减少了冗余探索。我们的代码可在以下网址获取：此https URL。
英文摘要
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 https://github.com/SYannL/nvdamas.
