Related papers: SpecEyes: Accelerating Agentic Multimodal LLMs via…

Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge monitoring (10-15%…

Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging due to two critical…

Improving time-to-first-token (TTFT) is an essentially important objective in modern large language model (LLM) inference engines. Optimizing TTFT directly results in higher maximal QPS and meets the requirements of many critical…

The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Language Model (LLM) inference. This challenge is particularly acute for emerging agentic applications that require processing multi-million…

Agentic Artificial Intelligence (AI) systems leveraging Large Language Models (LLMs) exhibit significant potential for complex reasoning, planning, and tool utilization. We demonstrate that a specialized computer vision system can be built…

Future sixth-generation (6G) mobile networks are envisioned to be equipped with a diverse set of powerful, yet highly specialized, optimization experts. Such a promising vision is concurrently expected to give rise to the need for scalable…

Large language models (LLMs) demonstrate impressive performance on a wide variety of tasks, but they often struggle with tasks that require multi-step reasoning or goal-directed planning. Both cognitive neuroscience and reinforcement…

Large language models (LLMs) exhibit strong symbolic and compositional reasoning, yet they struggle with time series question answering as the data is typically transformed into an LLM-compatible modality, e.g., serialized text, plotted…

As the development of AI-generated contents (AIGC), multi-modal Large Language Models (LLM) struggle to identify generated visual inputs from real ones. Such shortcoming causes vulnerability against visual deceptions, where the models are…

Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges…

Autoregressive decoding of large language models (LLMs) is memory bandwidth bounded, resulting in high latency and significant wastes of the parallel processing power of modern accelerators. Existing methods for accelerating LLM decoding…

Large language model-based deep research agents have been increasingly popular for addressing long-horizon information-seeking tasks, but they often incur high end-to-end latency due to extensive reasoning and frequent tool use. Speculation…

Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limited by its sequential…

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but optimizing LLM-based agentic systems remains challenging due to the vast search space of agent configurations, prompting strategies, and…

Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either…

We present Gradientsys, a next-generation multi-agent scheduling framework that coordinates diverse specialized AI agents using a typed Model-Context Protocol (MCP) and a ReAct-based dynamic planning loop. At its core, Gradientsys employs…

Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet…

Rollout dominates the training time in large language model (LLM) post-training, where the trained model is used to generate tokens given a batch of prompts. This work, SpecActor, achieves fast rollout with speculative decoding that deploys…

Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address…

Foundation models, e.g., large language models (LLMs), trained on internet-scale data possess zero-shot generalization capabilities that make them a promising technology towards detecting and mitigating out-of-distribution failure modes of…