Abstract--Deploying large language models (LLMs) on edge devices enables personalized agents with strong privacy and low cost. However, with tens to hundreds of billions of parameters, single-batch autoregressive inference suffers from extremely low arithmetic intensity, creating severe weight-loading and bandwidth pressures on resource-constrained platforms. Recent in-flash computing (IFC) solutions alleviate this bottleneck by co-locating weight-related linear computations in the decode phase with flash, yet still rely on DRAM for the key-value (KV) cache. As context length grows, the KV cache can exceed model weights in size, imposing prohibitive DRAM cost and capacity requirements. Attempts to offload KV cache to flash suffer from severe performance penalties. We propose KVNAND, the first DRAM-free, IFC-based architecture that stores both model weights and KV cache entirely in compute-enabled 3D NAND flash. KVNAND addresses the fundamental performance challenges of flash under intensive KV cache access by leveraging IFC for all memory-bound operations to reduce data transfer overhead, introducing head-group parallelism to boost throughput, and employing page-level KV cache mapping to align token access patterns with flash organization. In addition, we propose a design space exploration framework that evaluates discrete and compact KVNAND variants to balance weight and KV placement, automatically identifying the optimal design trade-off. These techniques mitigate latency, energy, and reliability concerns, turning flash into a practical medium for long-context KV storage. Evaluations on MHA 7B and GQA 70B LLMs show that KVNAND achieves 1.98 /1.94 /2.05 geomean speedup at 128/1K/10K-token contexts compared to DRAMequipped IFC designs and addresses out-of-memory failures at 100K context length. As Large Language Models (LLMs) integrate into daily workflows, demand increases for personalized AI agents that align with user preferences, domain knowledge, and interaction styles. Deploying such agents on edge devices offers privacy, low-latency responsiveness, and cost efficiency by eliminating cloud dependency, making on-device LLMs a compelling direction for AI democratization [81]. Realizing high-quality personal LLM agents on resource-limited edge devices faces two main bottlenecks: memory capacity and bandwidth. The growing demand for long-context agentic workflows like long document analysis [35], multi-turn dialogue [84], and chain-of-thought reasoning [10] introduces the KV cache as another dominant consumer of this limited memory [19], [74]. Moreover, recent state-of-the-art (SoT A) models support extensive context lengths ranging from 128K (LLaMA3.1-70B The KV cache demand scales linearly with context length; for example, a 13B model already requires 8 GB KV memory at a 10K context [71], placing prohibitive pressure on edge resources.

Abstract--This paper presents the V esselEdge system, which leverages federated learning and bandwidth-constrained trajectory compression to enhance maritime situational awareness by extending AIS coverage. V esselEdge transforms vessels into mobile sensors, enabling real-time anomaly detection and efficient data transmission over low-bandwidth connections. The system integrates the M fed model for federated learning and the BWC-DR-A algorithm for trajectory compression, prioritizing anomalous data. Preliminary results demonstrate the effectiveness of V esselEdge in improving AIS coverage and situational awareness using historical data. The Automatic Identification System (AIS) is a tracking system that uses transceivers on ships to monitor marine traffic.

Narratives are the cognitive and emotional scaffolds of propaganda. They organize isolated persuasive techniques into coherent stories that justify actions, attribute blame, and evoke identification with ideological camps. In this paper, we propose a novel fine-grained narrative classification in biased news articles. We also explore article-bias classification as the precursor task to narrative classification and fine-grained persuasive technique identification. We develop INDI-PROP, the first ideologically grounded fine-grained narrative dataset with multi-level annotation for analyzing propaganda in Indian news media. Our dataset INDI-PROP comprises 1,266 articles focusing on two polarizing socio-political events in recent times: CAA and the Farmers' protest. Each article is annotated at three hierarchical levels: (i) ideological article-bias (pro-government, pro-opposition, neutral), (ii) event-specific fine-grained narrative frames anchored in ideological polarity and communicative intent, and (iii) persuasive techniques. We propose FANTA and TPTC, two GPT-4o-mini guided multi-hop prompt-based reasoning frameworks for the bias, narrative, and persuasive technique classification. FANTA leverages multi-layered communicative phenomena by integrating information extraction and contextual framing for hierarchical reasoning. On the other hand, TPTC adopts systematic decomposition of persuasive cues via a two-stage approach. Our evaluation suggests substantial improvement over underlying baselines in each case.

We introduce a new approach to agent programming, the development of LLM-based agents. Current approaches to agent programming often entangle two aspects of agent design: the core workflow logic and the inference-time strategy (e.g., tree search). We introduce "probabilistic angelic nondeterminism" ("PAN"), a programming model that disentangles these two concerns, allowing the programmer to describe the agent workflow and independently experiment with different inference-time strategies by simply changing a few inputs. We provide an implementation of PAN in Python as the EnCompass framework, which uses a Python decorator to compile agent workflow programs into a search space. We present three case studies that demonstrate how the framework lets the programmer quickly improve the reliability of an agent and easily switch between different inference-time strategies, all with little additional coding.

Wireless sensor networks (WSNs) are employed across a wide range of industrial applications where ultra-low power consumption is a critical prerequisite. At the same time, these systems must maintain a certain level of determinism to ensure reliable and predictable operation. In this view, time slotted channel hopping (TSCH) is a communication technology that meets both conditions, making it an attractive option for its usage in industrial WSNs. This work proposes the use of machine learning to learn the traffic pattern generated in networks based on the TSCH protocol, in order to turn nodes into a deep sleep state when no transmission is planned and thus to improve the energy efficiency of the WSN. The ability of machine learning models to make good predictions at different network levels in a typical tree network topology was analyzed in depth, showing how their capabilities degrade while approaching the root of the tree. The application of these models on simulated data based on an accurate modeling of wireless sensor nodes indicates that the investigated algorithms can be suitably used to further and substantially reduce the power consumption of a TSCH network.

Diffusion models are renowned for their state-of-the-art performance in generating synthetic images. However, concerns related to safety, privacy, and copyright highlight the need for machine unlearning, which can make diffusion models forget specific training data and prevent the generation of sensitive or unwanted content. Current machine unlearning methods for diffusion models are primarily designed for conditional diffusion models and focus on unlearning specific data classes or features. Among these methods, finetuning-based machine unlearning methods are recognized for their efficiency and effectiveness, which update the parameters of pre-trained diffusion models by minimizing carefully designed loss functions. However, in this paper, we propose a novel attack named Diffusion Model Relearning Attack (DiMRA), which can reverse the finetuning-based machine unlearning methods, posing a significant vulnerability of this kind of technique. Without prior knowledge of the unlearning elements, DiMRA optimizes the unlearned diffusion model on an auxiliary dataset to reverse the unlearning, enabling the model to regenerate previously unlearned elements. To mitigate this vulnerability, we propose a novel machine unlearning method for diffusion models, termed as Diffusion Model Unlearning by Memorization (DiMUM). Unlike traditional methods that focus on forgetting, DiMUM memorizes alternative data or features to replace targeted unlearning data or features in order to prevent generating such elements. In our experiments, we demonstrate the effectiveness of DiMRA in reversing state-of-the-art finetuning-based machine unlearning methods for diffusion models, highlighting the need for more robust solutions. We extensively evaluate DiMUM, demonstrating its superior ability to preserve the generative performance of diffusion models while enhancing robustness against DiMRA.

In this study, we evaluate the efficacy of the Mamba model in the field of bioacoustics. We first pretrain a Mamba-based audio large language model (LLM) on a large corpus of audio data using self-supervised learning. We fine-tune and evaluate BioMamba on the BEANS benchmark, a collection of diverse bioacoustic tasks including classification and detection, and compare its performance and efficiency with multiple baseline models, including AVES, a state-of-the-art Transformer-based model. The results show that BioMamba achieves comparable performance with AVES while consumption significantly less VRAM, demonstrating its potential in this domain.

Despite recent advances, autonomous agents often struggle to solve complex tasks in enterprise domains that require coordinating multiple tools and processing diverse data sources. This struggle is driven by two main limitations. First, single-agent architectures enforce a monolithic plan-execute loop, which directly causes trajectory instability. Second, the requirement to use local open-weight models for data privacy introduces smaller context windows leading to the rapid consumption of context from large tool outputs. To solve this problem we introduce RP-ReAct (Reasoner Planner-ReAct), a novel multi-agent approach that fundamentally decouples strategic planning from low-level execution to achieve superior reliability and efficiency. RP-ReAct consists of a Reasoner Planner Agent (RPA), responsible for planning each sub-step, continuously analysing the execution results using the strong reasoning capabilities of a Large Reasoning Model, and one or multiple Proxy-Execution Agent (PEA) that translates sub-steps into concrete tool interactions using a ReAct approach. Crucially, we incorporate a context-saving strategy within the PEA to mitigate context window overflow by managing large tool outputs via external storage and on-demand access. We evaluate RP-ReAct, on the challenging, multi-domain ToolQA benchmark using a diverse set of six open-weight reasoning models. Our empirical results show that RP-ReAct achieves superior performance and improved generalization ability over state-of-the-art baselines when addressing diverse complex tasks across the evaluated domains. Furthermore we establish the enhanced robustness and stability of our approach across different model scales, paving the way for effective and deployable agentic solutions for enterprises.

The rise of Visual-Language Models (LVLMs) has unlocked new possibilities for seamlessly integrating visual and textual information. However, their ability to interpret cartographic maps remains largely unexplored. In this paper, we introduce CartoMapQA, a benchmark specifically designed to evaluate LVLMs' understanding of cartographic maps through question-answering tasks. The dataset includes over 2000 samples, each composed of a cartographic map, a question (with open-ended or multiple-choice answers), and a ground-truth answer. These tasks span key low-, mid- and high-level map interpretation skills, including symbol recognition, embedded information extraction, scale interpretation, and route-based reasoning. Our evaluation of both open-source and proprietary LVLMs reveals persistent challenges: models frequently struggle with map-specific semantics, exhibit limited geospatial reasoning, and are prone to Optical Character Recognition (OCR)-related errors. By isolating these weaknesses, CartoMapQA offers a valuable tool for guiding future improvements in LVLM architectures. Ultimately, it supports the development of models better equipped for real-world applications that depend on robust and reliable map understanding, such as navigation, geographic search, and urban planning. Our source code and data are openly available to the research community at: https://github.com/ungquanghuy-kddi/CartoMapQA.git

We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work.