Related papers: Token Coherence: Adapting MESI Cache Protocols to …

This position paper argues that agentic AI systems should be designed and evaluated as \emph{marginal token allocation economies} rather than as text generators priced by the unit. We follow a single request -- a developer asking a coding…

Cause-effect chains, as a widely used modeling method in real-time embedded systems, are extensively applied in various safety-critical domains. End-to-end latency, as a key real-time attribute of cause-effect chains, is crucial in many…

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is…

The rise of AI-native Low-Code/No-Code (LCNC) platforms enables autonomous agents capable of executing complex, long-duration business processes. However, a fundamental challenge remains: memory management. As agents operate over extended…

AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues…

The Transformer architecture, a cornerstone of modern Large Language Models (LLMs), has achieved extraordinary success in sequence modeling, primarily due to its attention mechanism. However, despite its power, the standard attention…

Driven by Large Language Models, the single-agent, multi-tool architecture has become a popular paradigm for autonomous agents. However, this architecture introduces a severe privacy risk, which we term Tools Orchestration Privacy Risk…

AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermediate state between steps and inflating end-to-end latency by 3-8x. We argue that this…

Disaggregating memory from compute offers the opportunity to better utilize stranded memory in cloud data centers. It is important to cache data in the compute nodes and maintain cache coherence across multiple compute nodes. However, the…

The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…

LLM agents are emerging as a key enabler for autonomous wireless network management. Reliably deploying them, however, demands benchmarks that reflect real engineering risk. Existing wireless benchmarks evaluate single isolated capabilities…

Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural…

To mitigate the ever worsening "Power wall" and "Memory wall" problems, multi-core architectures with multilevel cache hierarchies have been widely accepted in modern processors. However, the complexity of the architectures makes modeling…

Large language model (LLM)-based text-to-speech (TTS) systems achieve remarkable naturalness via autoregressive (AR) decoding, but require N sequential steps to generate N speech tokens. We present LLaDA-TTS, which replaces the AR LLM with…

The multiaccess coded caching (MACC) system, as formulated by Hachem {\it et al.}, consists of a central server with a library of $N$ files, connected to $K$ cache-less users via an error-free shared link, and $K$ cache nodes, each equipped…

With the increasing adoption of large language models (LLMs) in software engineering, the Chain of Thought (CoT) reasoning paradigm has become an essential approach for automated code repair. However, the explicit multi-step reasoning in…

We propose Text-Aligned Speech Tokens with Multiple Layer-Aggregation (TASLA), which is a text-aligned speech tokenization framework that aims to address the problem that under a low-frame-rate and text-aligned regime, single-source speech…

LLMs are increasingly used for software modernization, code translation, and database migration. However, LLM-based Oracle2PostgreSQL migration remains constrained by high token consumption, long-context degradation, dialect-specific…

Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce…