Related papers: MagicAgent: Towards Generalized Agent Planning

Fine-tuning on agent-environment interaction trajectory data holds significant promise for surfacing generalized agent capabilities in open-source large language models (LLMs). In this work, we introduce AgentBank, by far the largest…

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon…

The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS) has underscored the need for responsible and dependable system operation. Tools like LangChain and Retrieval-Augmented Generation have expanded LLM…

Large language models and autonomous AI agents have evolved rapidly, resulting in a diverse array of evaluation benchmarks, frameworks, and collaboration protocols. Driven by the growing need for standardized evaluation and integration, we…

Large language model (LLM)-based agents have demonstrated remarkable capabilities in decision-making tasks, but struggle significantly with complex, long-horizon planning scenarios. This arises from their lack of macroscopic guidance,…

Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…

Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation,…

Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows. In such settings, effective coordination cannot be fully designed in advance and…

Digital agents require diverse, large-scale UI trajectories to generalize across real-world tasks, yet collecting such data is prohibitively expensive in both human annotation, infra and engineering perspectives. To this end, we introduce…

AI agentic programming is an emerging paradigm where large language model (LLM)-based coding agents autonomously plan, execute, and interact with tools such as compilers, debuggers, and version control systems. Unlike conventional code…

The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered agents offer greater flexibility, cross-domain reasoning, and natural language interaction.…

The rapid advancement in generative pre-training models is propelling a paradigm shift in technological progression from basic applications such as chatbots towards more sophisticated agent-based systems. It is with huge potential and…

Large language model based multi-agent systems have demonstrated significant potential in social simulation and complex task resolution domains. However, current frameworks face critical challenges in system architecture design,…

Large Language Model (LLM)-powered agents have unlocked new possibilities for automating human tasks. While prior work has focused on well-defined tasks with specified goals, the capabilities of agents in creative design tasks with…

Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of…

Human communication is a complex and diverse process that not only involves multiple factors such as language, commonsense, and cultural backgrounds but also requires the participation of multimodal information, such as speech. Large…

The concept of the 'agent' has profoundly shaped Artificial Intelligence (AI) research, guiding development from foundational theories to contemporary applications like Large Language Model (LLM)-based systems. This paper critically…

Building effective clinical decision support systems requires the synthesis of complex heterogeneous multimodal data. Such modalities include temporal electronic health records data, medical images, radiology reports, and clinical notes.…

While Vision-Language-Action (VLA) models have demonstrated impressive capabilities in robotic manipulation, their performance in complex reasoning and long-horizon task planning is limited by data scarcity and model capacity. To address…

The rapid advancement of large language models (LLMs) has led to the rise of LLM-based agents. Recent research shows that multi-agent systems (MAS), where each agent plays a specific role, can outperform individual LLMs. However,…