Related papers: HiVA: Self-organized Hierarchical Variable Agent v…
The integration of Large Language Models (LLMs) with specialized tools presents new opportunities for intelligent automation systems. However, orchestrating multiple LLM-driven agents to tackle complex tasks remains challenging due to…
It has been widely recognized that the performance of a multi-agent system is highly affected by its organization. A large scale system may have billions of possible ways of organization, which makes it impractical to find an optimal choice…
Open-ended self-improving agents can autonomously modify their own structural designs to advance their capabilities and overcome the limits of pre-defined architectures, thus reducing reliance on human intervention. We introduce…
Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world problems, especially in scientific…
The remarkable progress of vision-language models (VLMs) has enabled GUI agents to interact with computers in a human-like manner. Yet real-world computer-use tasks remain difficult due to long-horizon workflows, diverse interfaces, and…
Model-based reasoning agents are ill-equipped to act in novel situations in which their model of the environment no longer sufficiently represents the world. We propose HYDRA - a framework for designing model-based agents operating in mixed…
The rapid advancement of large language models (LLMs) has transformed the landscape of agentic information seeking capabilities through the integration of tools such as search engines and web browsers. However, current mainstream approaches…
Models of human motion commonly focus either on trajectory prediction or action classification but rarely both. The marked heterogeneity and intricate compositionality of human motion render each task vulnerable to the data degradation and…
This paper proposes EvoAgent - an evolvable large language model (LLM) agent framework that integrates structured skill learning with a hierarchical sub-agent delegation mechanism. EvoAgent models skills as multi-file structured capability…
User-Centric Embodied Visual Tracking (UC-EVT) presents a novel challenge for reinforcement learning-based models due to the substantial gap between high-level user instructions and low-level agent actions. While recent advancements in…
Recent advancements indicate that scaling up Multimodal Large Language Models (MLLMs) effectively enhances performance on downstream multimodal tasks. The prevailing MLLM paradigm, \emph{e.g.}, LLaVA, transforms visual features into…
Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to…
LLM-powered tool-calling agents fulfill user requests by interacting with environments, querying data, and invoking tools in a multi-turn process. Yet, most existing benchmarks evaluate these systems under static environment interfaces,…
Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenEnv, a framework that establishes a difficulty-aligned…
Test-time adaptation allows pretrained models to adjust to incoming data streams, addressing distribution shifts between source and target domains. However, standard methods rely on single-dimensional linear classification layers, which…
Autonomous inspection systems are essential for ensuring the performance and longevity of industrial assets. Recently, agentic frameworks have demonstrated significant potential for automating inspection workflows but have been limited to…
Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after…
Coordination among connected and autonomous vehicles (CAVs) is advancing due to developments in control and communication technologies. However, much of the current work is based on oversimplified and unrealistic task-specific assumptions,…
As Large Language Models (LLMs) are increasingly deployed as autonomous agents, they face a critical scalability bottleneck known as the "Generalization-Specialization Dilemma." Monolithic agents equipped with extensive toolkits suffer from…
As multimodal LLM-driven agents advance in autonomy and generalization, traditional static datasets face inherent scalability limitations and are insufficient for fully assessing their capabilities in increasingly complex and diverse tasks.…