Related papers: EvoCUA: Evolving Computer Use Agents via Learning …
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…
Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing approaches to improving agent performance often rely on modifying the agent itself -- through…
Embodied Artificial Intelligence (AI) is an intelligent system formed by agents and their environment through active perception, embodied cognition, and action interaction. Existing embodied AI remains confined to human-crafted setting, in…
We propose a lifelong learning architecture, the Neural Computer Agent (NCA), where a Reinforcement Learning agent is paired with a predictive model of the environment learned by a Differentiable Neural Computer (DNC). The agent and DNC…
Graphical User Interface (GUI) agents show great potential for enabling foundation models to complete real-world tasks, revolutionizing human-computer interaction and improving human productivity. In this report, we present OmegaUse, a…
General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling…
With the advent of generative AI and large language models, embodied conversational agents are becoming synonymous with online interactions. These agents possess vast amounts of knowledge but suffer from exhibiting limited emotional…
This paper proposes an intelligent service optimization method based on a multi-agent collaborative evolution mechanism to address governance challenges in large-scale microservice architectures. These challenges include complex service…
Edge computing breaks with traditional autoscaling due to strict resource constraints, thus, motivating more flexible scaling behaviors using multiple elasticity dimensions. This work introduces an agent-based autoscaling framework that…
Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…
Prevailing medical AI operates on an unrealistic ''one-shot'' model, diagnosing from a complete patient file. However, real-world diagnosis is an iterative inquiry where Clinicians sequentially ask questions and order tests to strategically…
To unleash the full potential of AI for Science, we must untether the agents from a purely digital environment. The agent's ability to control and explore in real-world labs is essential because the physical lab remains foundational to…
Rapid advances in large language models and agentic AI are driving the emergence of the Internet of Agents (IoA), a paradigm where billions of autonomous software and embodied agents interact, coordinate, and collaborate to accomplish…
Due to the complexity of the natural world, a programmer cannot foresee all possible situations, a connected and autonomous vehicle (CAV) will face during its operation, and hence, CAVs will need to learn to make decisions autonomously. Due…
Realizing endogenous narrative evolution in LLM-based multi-agent systems is hindered by the inherent stochasticity of generative emergence. In particular, long-horizon simulations suffer from social memory stacking, where conflicting…
Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-specific integrations. Despite recent…
Long-horizon robotic manipulation remains challenging for Vision-Language-Action (VLA) models despite recent progress in zero-shot generalization and simulation-to-real-world transfer. Current VLA models suffer from stage hallucination,…
We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as…
Computer-use agents that combine GUI interaction with structured API calls via the Model Context Protocol (MCP) show promise for automating software tasks. However, existing approaches lack a principled understanding of how agents should…
Embodied systems, where generative autonomous agents engage with the physical world through integrated perception, cognition, action, and advanced reasoning powered by large language models (LLMs), hold immense potential for addressing…