Search papers, labs, and topics across Lattice.
MemFactory is introduced as a unified framework for training and inference of memory-augmented LLM agents, addressing the fragmented landscape of existing implementations. It abstracts the memory lifecycle into modular components, allowing for flexible agent construction and integration of Group Relative Policy Optimization (GRPO) for memory management fine-tuning. Empirical validation on the MemAgent architecture demonstrates performance improvements of up to 14.8% in both in-domain and out-of-distribution settings.
Stop cobbling together memory-augmented agents: MemFactory offers a unified "Lego-like" framework that streamlines training and boosts performance by up to 14.8%.
Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recently, applying Reinforcement Learning (RL) to optimize memory operations, such as extraction, updating, and retrieval, has emerged as a highly promising research direction. However, existing implementations remain highly fragmented and task-specific, lacking a unified infrastructure to streamline the integration, training, and evaluation of these complex pipelines. To address this gap, we present MemFactory, the first unified, highly modular training and inference framework specifically designed for memory-augmented agents. Inspired by the success of unified fine-tuning frameworks like LLaMA-Factory, MemFactory abstracts the memory lifecycle into atomic, plug-and-play components, enabling researchers to seamlessly construct custom memory agents via a"Lego-like"architecture. Furthermore, the framework natively integrates Group Relative Policy Optimization (GRPO) to fine-tune internal memory management policies driven by multi-dimensional environmental rewards. MemFactory provides out-of-the-box support for recent cutting-edge paradigms, including Memory-R1, RMM, and MemAgent. We empirically validate MemFactory on the open-source MemAgent architecture using its publicly available training and evaluation data. Across both in-domain and out-of-distribution evaluation sets, MemFactory consistently improves performance over the corresponding base models, with relative gains of up to 14.8%. By providing a standardized, extensible, and easy-to-use infrastructure, MemFactory significantly lowers the barrier to entry, paving the way for future innovations in memory-driven AI agents.