Related papers: XGrammar-2: Efficient Dynamic Structured Generatio…

The deployment and scaling of large language models (LLMs) have become critical as they permeate various applications, demanding high-throughput and low-latency serving systems. Existing frameworks struggle to balance these requirements,…

Automatic search for Multi-Agent Systems has recently emerged as a key focus in agentic AI research. Several prior approaches have relied on LLM-based free-form search over the code space. In this work, we propose a more structured…

Agentic AI is rapidly transitioning from research prototypes to enterprise deployments, where requirements extend to meet the software quality attributes of reliability, scalability, and observability beyond plausible text generation. We…

Recent advances in graph learning have paved the way for innovative retrieval-augmented generation (RAG) systems that leverage the inherent relational structures in graph data. However, many existing approaches suffer from rigid, fixed…

Modern information systems require autonomous agents capable of navigating complex workflows, yet current methodologies often struggle with the transition from structured metadata parsing to general environmental perception. While the…

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI experts. Existing research in prompt engineering suggests…

Accelerating large language model pre-training is a critical issue in present research. In this paper, we focus on speeding up pre-training by progressively growing from a small Transformer structure to a large one. There are two main…

While humans naturally learn and adapt from past experiences, large language models (LLMs) and their agentic counterparts struggle to retain reasoning from previous tasks and apply them in future contexts. To address this limitation, we…

Although Large Language Models (LLMs) demonstrate significant capabilities, their reliance on parametric knowledge often leads to inaccuracies. Retrieval Augmented Generation (RAG) mitigates this by incorporating external knowledge, but…

Large language model(LLM)-driven multi-agent systems(MAS) coordinate specialized agents through predefined interaction topologies and have shown promise for complex tasks such as competition-level code generation. Recent studies demonstrate…

Retrieval-augmented generation (RAG) has emerged as a pivotal method for expanding the knowledge of large language models. To handle complex queries more effectively, researchers developed Adaptive-RAG (A-RAG) to enhance the generated…

Deploying Large Language Model (LLM) applications, particularly those relying on Retrieval-Augmented Generation (RAG), remains challenging due to high computational demands, outdated knowledge bases, and the need to manually select optimal…

Large Language Models (LLMs) such as GPT-4 and Llama3 can already comprehend complex commands and process diverse tasks. This advancement facilitates their application in controlling drones and robots for various tasks. However, existing…

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful…

Early-stage engineering design involves complex, iterative reasoning, yet existing large language model (LLM) workflows struggle to maintain task continuity and generate executable models. We evaluate whether a structured multi-agent system…

Graph Retrieval-Augmented Generation (GraphRAG) enhances factual reasoning in LLMs by structurally modeling knowledge through graph-based representations. However, existing GraphRAG approaches face two core limitations: shallow retrieval…

Time consumption and the complexity of manual layout design make automated layout generation a critical task, especially for multiple applications across different mobile devices. Existing graph-based layout generation approaches suffer…

Multimodal Foundation Models (MMFMs) have demonstrated strong performance in both computer vision and natural language processing tasks. However, their performance diminishes in tasks that require a high degree of integration between these…

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to instruct LLMs proficiently poses a challenge for non-AI experts. Existing research in prompt engineering suggests…

Speech generation models based on large language models (LLMs) typically operate on discrete acoustic codes, which differ fundamentally from text tokens due to their multicodebook structure. At each timestep, models must predict N codebook…