Autonomous agents, tool use, and agentic systems
![[2601.00809] A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2601.00809: A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction
Abstract page for arXiv paper 2511.11483: ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation
Abstract page for arXiv paper 2410.09134: Multi-Agent Actor-Critics in Autonomous Cyber Defense
The article presents TCM-DiffRAG, a novel reasoning framework for Traditional Chinese Medicine (TCM) that enhances diagnosis through know...
This article explores the concept of modality collapse in multimodal large language models (LLMs), highlighting the limitations of decode...
This paper presents FatsMB, a novel framework for Multi-Behavior Sequential Recommendation (MBSR) that enhances user preference modeling ...
This article presents a study on the operational validity of using Large Language Models (LLMs) to simulate social media user behavior th...
MoDora is a novel LLM-powered system designed for analyzing semi-structured documents, addressing challenges in information retrieval and...
The paper presents AMLRIS, a novel training strategy for Referring Image Segmentation (RIS) that enhances object segmentation through ali...
This article presents a novel approach to augmented reading systems, proposing a simulation-based optimization framework that enhances te...
AgentSentry introduces a novel framework to mitigate indirect prompt injection (IPI) in LLM agents, enhancing their security while mainta...
This study explores how modality affects preference alignment in AI systems, comparing human and synthetic evaluations of audio and text ...
This paper presents KGT, a novel framework addressing the granularity mismatch between large language models (LLMs) and knowledge graphs ...
The paper presents pMoE, a novel Mixture-of-Experts prompt tuning method that enhances visual adaptation by integrating diverse domain kn...
This paper explores the behavior of wide Bayesian neural networks, focusing on rare fluctuations that influence posterior concentration b...
The paper introduces SUPERGLASSES, a benchmark for evaluating Vision Language Models (VLMs) in AI smart glasses, addressing the limitatio...
The paper presents InteractCS-RL, a novel framework for enhancing task-oriented dialogue systems by balancing empathetic communication an...
The paper presents PSQE, a method for enhancing pseudo seed quality in unsupervised multimodal entity alignment, addressing challenges in...
This paper presents a novel approach to instruction-based image editing by integrating planning, reasoning, and generation through a mult...
This article presents a novel framework for Unsupervised Continual Learning in Amortized Bayesian Inference, addressing performance issue...
This article explores the application of diffusion models in end-to-end autonomous driving, demonstrating their effectiveness through ext...
CoLyricist is an AI-assisted tool designed to enhance the lyric writing process by aligning with the common workflows of lyricists, impro...
The paper introduces QSIM, a novel framework that addresses the issue of Q-value overestimation in multi-agent reinforcement learning (MA...
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime