AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Att

arXiv:2606.11680v1 Announce Type: new Abstract: Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant

arXiv:2605.00254v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) architectures have turned LLM serving into a cluster-scale workload in which communication consumes a

arXiv:2608.23807v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) can in principle generate text faster than autoregressive (AR) models, since they denoise

arXiv:2605.19593v1 Announce Type: new Abstract: Modern deployments of Large Language Models (LLMs) increasingly require serving multiple models with diverse architectures, sizes,

arXiv:2603.18743v1 Announce Type: new Abstract: We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing

arXiv:2604.01007v1 Announce Type: new Abstract: AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal

arXiv:2604.15357v1 Announce Type: cross Abstract: Precise estimation of model inference latency is crucial for time-critical mobile edge applications, enabling devices to

arXiv:2608.17336v1 Announce Type: new Abstract: Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention