arXiv subjects

Ziliang Guo

Publications and source records attributed to Ziliang Guo.

5 recordsLinked to original sources

arXiv2026

Metis: Memory Foundation Model

Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reasoning models. However, agent memory is still primarily implemented through external modules, leaving the native memory capability largely unexplored. In this paper, we take a first step toward this direction by introducing memory foundation models, which empower foundation models with native memory capabilities. We formalize native memory from two perspectives: a persistent and dynamically evolving memory state within the backbone, and native memory procedures that autonomously store and utilize information through model computation. We show that native memory offers advantages in architecture, end-to-end optimization, and efficiency. Based on this formulation, we propose Metis, the first prototype of memory foundation models. Metis introduces a new architecture that equips a foundation model with a native memory state, allowing historical information to be compressed into the model and accessed through memory attention. We construct large-scale memory-specific training data and introduce multiple optimization objectives to acquire these native memory procedures through mid-training. The online memory maintenance of Metis is gradient-free, and the memory update requires only a forward pass. At inference time, all learned model weights remain frozen, while the native memory states are autonomously transformed through standard forward computation. Through extensive experiments, we show that Metis exhibits native memory capabilities and further provide a detailed analysis of its strengths, limitations, and behaviors. To facilitate future research on memory foundation models, we release our project and model checkpoints.

cs.CL↗

arXiv2026

MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations

Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing benchmarks, however, evaluate such memory almost exclusively through downstream question answering, scoring only the correctness of a final answer. This black-box formulation conflates the heterogeneous causes of memory failure, such as missing the introduction of a relevant fact, binding an operation to the wrong target, or relying on stale values after a correction. As a result, it can credit correct answers despite their reliance on inconsistent or unsafe memory states. In this paper, we argue that, in dynamic long-horizon interactions, memory is not a static collection of facts but a lifecycle of explicit operations, including remembering, forgetting, updating, reflecting, and their compositions. We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations and represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence. A controllable generation pipeline embeds these operations into long, task-oriented conversations and produces gold operation traces together with six categories of operation-level probes, evaluated under both adjacent-evidence and long-context settings. Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals, revealing that current systems remain far from uniformly reliable. For instance, session-level retrieval outperforms turn-level retrieval, and long-context models remain notably weak at reconstructing ordered memory-state trajectories. These results move long-term memory evaluation from final-answer scoring toward interpretable, operation-level diagnosis.

cs.AI↗

arXiv2026

MemFactory: Unified Inference & Training Framework for Agent Memory

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 the evaluation sets, MemFactory improves performance over the corresponding base models on average, 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.

cs.CL↗

arXiv2026

Reconfigurable Oxide Nanoelectronics by Tip-induced Electron Delocalization

Reconfigurable oxide nanoelectronics, enabled by conductive atomic force microscope (cAFM) lithography, have established complex oxide interfaces as a promising platform for quantum engineering that harnesses emergent phenomena for advanced functionalities. However, this cAFM nanofabrication process can only occur in the air, with simultaneous device decay described under the "water-cycle" writing mechanism. These restrictions pose ongoing challenges for device optimization in the quantum regime at mK temperatures. Here, we demonstrate a "waterless" cAFM lithography approach that is compatible with vacuum and cryogenic environments. Through oxygen vacancy engineering at the LaAlO$_3$/SrTiO$_3$ interface, we have achieved nonvolatile and reconfigurable cAFM control of nanoscale interfacial polaron-electron liquid transition at mK temperatures with an ultrafine line resolution of 0.85 nm. Supported by first-principles calculations and drift-diffusion modeling, we show that tip-controlled oxygen vacancy electromigration plays a key role. This advancement bridges reconfigurable device fabrication and concurrent characterization in situ at mK temperatures, and establishes a versatile Hubbard toolbox for engineering programmable quantum phases in correlated oxides.

cond-mat.mes-hall↗

arXiv2025

A Milli-Kelvin Atomic Force Microscope Made of Glass

Milli-Kelvin atomic force microscopy (mK-AFM) presents an ongoing experimental challenge due to the intense vibrations in a cryogen-free dilution refrigerator and the low cooling power available at mK temperatures. A viable approach is to make the system exceptionally rigid and thermally insulating to decouple external vibrations and isolate heat dissipation from the piezo elements. Here, we present a low-cost and large scan-range mK-AFM that operates below 100 mK. All the essential parts of our mK-AFM, including the scanners, tip assembly, and microscope body, are custom-made of fused silica glass by taking advantage of its high specific modulus, extremely low thermal expansion coefficient, and excellent thermal insulation properties. We carefully balance the scan range (25 $μ$m $\times$ 25 $μ$m), heat dissipation, and stiffness of the system to reach optimal performance at mK temperatures.

physics.ins-det↗