MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exposes sensitive user information, while existing privacy protection methods typically rely on aggressive masking that removes task-relevant semantics and consequently degrades memory utility and personalization quality. To address this challenge, We propose MemPrivacy, which identifies privacy-sensitive spans on edge devices, replaces them with semantically structured type-aware placeholders for cloud-side memory processing, and restores the original values locally when needed. By decoupling privacy protection from semantic destruction, MemPrivacy minimizes sensitive data exposure while retaining the information required for effective memory formation and retrieval. We also construct MemPrivacy-Bench for systematic evaluation, a dataset covering 200 users and over 52k privacy instances, and introduce a four-level privacy taxonomy for configurable protection policies. Experiments show that MemPrivacy achieves strong performance in privacy information extraction, substantially surpassing strong general-purpose models such as GPT-5.2 and Gemini-3.1-Pro, while also reducing inference latency. Across multiple widely used memory systems, MemPrivacy limits utility loss to within 1.6%, outperforming baseline masking strategies. Overall, MemPrivacy offers an effective balance between privacy protection and personalized memory utility for edge-cloud agents, enabling secure, practical, and user-transparent deployment.

MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval

In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage paradigm, but generic reranking models rely on semantic similarity matching and lack genuine reasoning capabilities, leading to a problem where recalled results are semantically highly relevant yet do not contain the key information needed to answer the question. This deficiency manifests in memory scenarios as three specific problems. First, relevance scores are miscalibrated, making threshold-based filtering difficult. Second, ranking degrades when facing temporal constraints, causal reasoning, and other complex queries. Third, the model cannot leverage dialogue context for semantic disambiguation. This report introduces MemReranker, a reranking model family (0.6B/4B) built on Qwen3-Reranker through multi-stage LLM knowledge distillation. Multi-teacher pairwise comparisons generate calibrated soft labels, BCE pointwise distillation establishes well-distributed scores, and InfoNCE contrastive learning enhances hard-sample discrimination. Training data combines general corpora with memory-specific multi-turn dialogue data covering temporal constraints, causal reasoning, and coreference resolution. On the memory retrieval benchmark, MemReranker-0.6B substantially outperforms BGE-Reranker and matches open-source 4B/8B models as well as GPT-4o-mini on key metrics. MemReranker-4B further achieves 0.737 MAP, with several metrics on par with Gemini-3-Flash, while maintaining inference latency at only 10--20\% of large models. On finance and healthcare vertical-domain benchmarks, the models preserve generalization capabilities on par with mainstream large-parameter rerankers.

MemReader: From Passive to Active Extraction for Long-Term Agent Memory

Long-term memory is fundamental for personalized and autonomous agents, yet populating it remains a bottleneck. Existing systems treat memory extraction as a one-shot, passive transcription from context to structured entries, which struggles with noisy dialogue, missing references, and cross-turn dependencies, leading to memory pollution, low-value writes, and inconsistency. In this paper, we introduce the MemReader family for active long-term memory extraction in agent systems: MemReader-0.6B, a compact and cost-efficient passive extractor distilled for accurate and schema-consistent structured outputs, and MemReader-4B, an active extractor optimized with Group Relative Policy Optimization (GRPO) to make memory writing decisions. Under a ReAct-style paradigm, MemReader-4B explicitly evaluates information value, reference ambiguity, and completeness before acting, and can selectively write memories, defer incomplete inputs, retrieve historical context, or discard irrelevant chatter. Experiments on LOCOMO, LongMemEval, and HaluMem show that MemReader consistently outperforms existing extraction-based baselines. In particular, MemReader-4B achieves state-of-the-art performance on tasks involving knowledge updating, temporal reasoning, and hallucination reduction. These results suggest that effective agent memory requires not merely extracting more information, but performing reasoning-driven and selective memory extraction to build low-noise and dynamically evolving long-term memory. Furthermore, MemReader has been integrated into MemOS and is being deployed in real-world applications. To support future research and adoption, we release the models and provide public API access.

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.

PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments

Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. However, prior evaluations typically interleave preference-related dialogues with irrelevant conversations, reducing the task to needle-in-a-haystack retrieval while ignoring relationships between events that drive the evolution of user preferences. Such settings overlook a fundamental characteristic of real-world personalization: preferences emerge gradually and accumulate across interactions within noisy contexts. To bridge this gap, we introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall. Additionally, we incorporate (1) text variability and (2) linguistic alignment to simulate erratic user inputs and individual idiolects in real-world data. PERMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time. We design both multiple-choice and interactive tasks to probe the model's understanding of persona along the interaction timeline. Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption, outperforming traditional semantic retrieval of raw dialogues. Nevertheless, they still struggle to maintain a coherent persona across temporal depth and cross-domain interference, highlighting the need for more robust personalized memory management in agents. Our code and data are open-sourced at https://github.com/PolarisLiu1/PERMA.

Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis

Deploying Large Language Models to data-scarce programming domains poses significant challenges, particularly for kernel synthesis on emerging Domain-Specific Architectures where a "Data Wall" limits available training data. While models excel on data-rich platforms like CUDA, they suffer catastrophic performance drops on data-scarce ecosystems such as NPU programming. To overcome this cold-start barrier without expensive fine-tuning, we introduce EvoKernel, a self-evolving agentic framework that automates the lifecycle of kernel synthesis from initial drafting to continual refining. EvoKernel addresses this by formulating the synthesis process as a memory-based reinforcement learning task. Through a novel value-driven retrieval mechanism, it learns stage-specific Q-values that prioritize experiences based on their contribution to the current objective, whether bootstrapping a feasible draft or iteratively refining latency. Furthermore, by enabling cross-task memory sharing, the agent generalizes insights from simple to complex operators. By building an NPU variant of KernelBench and evaluating on it, EvoKernel improves frontier models' correctness from 11.0% to 83.0% and achieves a median speedup of 3.60x over initial drafts through iterative refinement. This demonstrates that value-guided experience accumulation allows general-purpose models to master the kernel synthesis task on niche hardware ecosystems. Our official page is available at https://evokernel.zhuo.li.

AlayaLaser: Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search

On-disk graph-based approximate nearest neighbor search (ANNS) is essential for large-scale, high-dimensional vector retrieval, yet its performance is widely recognized to be limited by the prohibitive I/O costs. Interestingly, we observed that the performance of on-disk graph-based index systems is compute-bound, not I/O-bound, with the rising of the vector data dimensionality (e.g., hundreds or thousands). This insight uncovers a significant optimization opportunity: existing on-disk graph-based index systems universally target I/O reduction and largely overlook computational overhead, which leaves a substantial performance improvement space. In this work, we propose AlayaLaser, an efficient on-disk graph-based index system for large-scale high-dimensional vector similarity search. In particular, we first conduct performance analysis on existing on-disk graph-based index systems via the adapted roofline model, then we devise a novel on-disk data layout in AlayaLaser to effectively alleviate the compute-bound, which is revealed by the above roofline model analysis, by exploiting SIMD instructions on modern CPUs. We next design a suite of optimization techniques (e.g., degree-based node cache, cluster-based entry point selection, and early dispatch strategy) to further improve the performance of AlayaLaser. We last conduct extensive experimental studies on a wide range of large-scale high-dimensional vector datasets to verify the superiority of AlayaLaser. Specifically, AlayaLaser not only surpasses existing on-disk graph-based index systems but also matches or even exceeds the performance of in-memory index systems.

Efficient Anti-exploration via VQVAE and Fuzzy Clustering in Offline Reinforcement Learning

Pseudo-count is an effective anti-exploration method in offline reinforcement learning (RL) by counting state-action pairs and imposing a large penalty on rare or unseen state-action pair data. Existing anti-exploration methods count continuous state-action pairs by discretizing these data, but often suffer from the issues of dimension disaster and information loss in the discretization process, leading to efficiency and performance reduction, and even failure of policy learning. In this paper, a novel anti-exploration method based on Vector Quantized Variational Autoencoder (VQVAE) and fuzzy clustering in offline RL is proposed. We first propose an efficient pseudo-count method based on the multi-codebook VQVAE to discretize state-action pairs, and design an offline RL anti-exploitation method based on the proposed pseudo-count method to handle the dimension disaster issue and improve the learning efficiency. In addition, a codebook update mechanism based on fuzzy C-means (FCM) clustering is developed to improve the use rate of vectors in codebooks, addressing the information loss issue in the discretization process. The proposed method is evaluated on the benchmark of Datasets for Deep Data-Driven Reinforcement Learning (D4RL), and experimental results show that the proposed method performs better and requires less computing cost in multiple complex tasks compared to state-of-the-art (SOTA) methods.

AI-Driven Fuzzing for Vulnerability Assessment of 5G Traffic Steering Algorithms

Traffic Steering (TS) dynamically allocates user traffic across cells to enhance Quality of Experience (QoE), load balance, and spectrum efficiency in 5G networks. However, TS algorithms remain vulnerable to adversarial conditions such as interference spikes, handover storms, and localized outages. To address this, an AI-driven fuzz testing framework based on the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) is proposed to systematically expose hidden vulnerabilities. Using NVIDIA Sionna, five TS algorithms are evaluated across six scenarios. Results show that AI-driven fuzzing detects 34.3% more total vulnerabilities and 5.8% more critical failures than traditional testing, achieving superior diversity and edge-case discovery. The observed variance in critical failure detection underscores the stochastic nature of rare vulnerabilities. These findings demonstrate that AI-driven fuzzing offers an effective and scalable validation approach for improving TS algorithm robustness and ensuring resilient 6G-ready networks.

FairShare: Auditable Geographic Fairness for Multi-Operator LEO Spectrum Sharing

Dynamic spectrum sharing (DSS) among multi-operator low Earth orbit (LEO) mega-constellations is essential for coexistence, yet prevailing policies focus almost exclusively on interference mitigation, leaving geographic equity largely unaddressed. This work investigates whether conventional DSS approaches inadvertently exacerbate the rural digital divide. Through large-scale, 3GPP-compliant non-terrestrial network (NTN) simulations with geographically distributed users, we systematically evaluate standard allocation policies. The results uncover a stark and persistent structural bias: SNR-priority scheduling induces a 1.65x urban-rural access disparity, privileging users with favorable satellite geometry. Counter-intuitively, increasing system bandwidth amplifies rather than alleviates this gap, with disparity rising from 1.0x to 1.65x as resources expand. To remedy this, we propose FairShare, a lightweight, quota-based framework that enforces geographic fairness. FairShare not only reverses the bias, achieving an affirmative disparity ratio of Delta_geo = 0.72x, but also reduces scheduler runtime by 3.3%. This demonstrates that algorithmic fairness can be achieved without trading off efficiency or complexity. Our work provides regulators with both a diagnostic metric for auditing fairness and a practical, enforceable mechanism for equitable spectrum governance in next-generation satellite networks.