Related papers: SkillWeaver: Web Agents can Self-Improve by Discov…
Vast quantities of compute (GPU cycles on personal workstations, idle inference servers, and edge devices between jobs) go unused because no incentive-aligned protocol exists for their owners to share them safely and profitably. Existing…
AI Agents are changing the way work gets done, both in consumer and enterprise domains. However, the design patterns and architectures to build highly capable agents or multi-agent systems are still developing, and the understanding of the…
Recent advancements in Large Language Models (LLMs) and multimodal counterparts have spurred significant interest in developing web agents -- AI systems capable of autonomously navigating and completing tasks within web environments. While…
Healthcare automation is shaped by local procedures and organizational constraints, so agent capabilities rarely transfer unchanged across settings. Agent skills, self-contained directories that package reusable procedures for AI agents,…
The efficacy of AI agents in healthcare research is hindered by their reliance on static, predefined strategies. This creates a critical limitation: agents can become better tool-users but cannot learn to become better strategic planners, a…
In the realm of web agent research, achieving both generalization and accuracy remains a challenging problem. Due to high variance in website structure, existing approaches often fail. Moreover, existing fine-tuning and in-context learning…
Autonomous embodied agents live on an Internet of multimedia websites. Can they hop around multimodal websites to complete complex user tasks? Existing benchmarks fail to assess them in a realistic, evolving environment for their embodiment…
Web agents require both high-level reasoning (for task decomposition) and low-level interactions (for page elements manipulation) to conduct different tasks. However, these knowledge types differ fundamentally: reasoning knowledge (e.g.,…
AI agents -- systems that execute multi-step reasoning workflows with persistent state, tool access, and specialist skills -- represent a qualitative shift from prior automation technologies in social science. Unlike chatbots that respond…
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…
With the advancement of vision-language models, web automation has made significant progress. However, deploying autonomous agents in real-world settings remains challenging, primarily due to site heterogeneity, where generalist models lack…
The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistants. However, training these agents is severely hampered by…
With the advancement of web techniques, they have significantly revolutionized various aspects of people's lives. Despite the importance of the web, many tasks performed on it are repetitive and time-consuming, negatively impacting overall…
Deploying LLM-powered agents in enterprise scenarios such as cloud technical support demands high-quality, domain-specific skills. However, existing skill creators lack domain grounding, producing skills poorly aligned with real-world task…
Previous research has demonstrated the potential of AI agents to act as companions that can provide constant emotional support for humans. In this paper, we emphasize the necessity of autonomous adaptation in personal AI companionship, an…
Agent-to-Agent (A2A) networks enable autonomous AI agents to collaborate by sharing reusable problem-solving instructions. However, how these decentralized ecosystems operate in practice remains largely unexplored. We present the first…
As full AI-based automation remains out of reach in most real-world applications, the focus has instead shifted to leveraging the strengths of both human and AI agents, creating effective collaborative systems. The rapid advances in this…
Improvements in the area of large language models have shifted towards the construction of models capable of using external tools and interpreting their outputs. These so-called web agents have the ability to interact autonomously with the…
Long-horizon code generation requires sustained context and adaptive expertise across domains. Current multi-agent systems use static workflows that cannot adapt when runtime analysis reveals unanticipated complexity. We propose AgentSpawn,…
Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenges, existing research has focused on crafting multi-agent systems with agentic workflows, where…