Related papers: Agent Primitives: Reusable Latent Building Blocks …

Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low…

Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language…

Large Language Models (LLMs) have demonstrated the ability to solve a wide range of practical tasks within multi-agent systems. However, existing human-designed multi-agent frameworks are typically limited to a small set of pre-defined…

Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks. However, these agents often suffer from high latency and low…

Multi-agent systems (MAS) and reinforcement learning (RL) are widely used to enhance the agentic capabilities of large language models (LLMs). MAS improves task performance through role-based orchestration, while RL uses environmental…

With the development of foundation model (FM), agentic AI systems are getting more attention, yet their inherent issues like hallucination and poor reasoning, coupled with the frequent ad-hoc nature of system design, lead to unreliable and…

Multi-agent systems (MAS) composed of large language models often exhibit improved problem-solving performance despite operating on identical information. In this work, we provide a formal explanation for this phenomenon grounded in…

Multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. Recent work has explored self-evolving MAS that automatically optimize agent capabilities or communication topologies. However, existing methods…

Multi-agent systems (MAS) powered by Large Language Models (LLMs) have been demonstrated to push the boundaries of LLM capabilities, yet they often incur significant costs and face challenges in dynamic LLM selection. Current LLM routing…

Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency. However, optimizing these systems often requires labor-intensive, manual adjustments to refine roles, tasks, and…

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack…

In architectural interior design, miscommunication frequently arises as clients lack design knowledge, while designers struggle to explain complex spatial relationships, leading to delayed timelines and financial losses. Recent advancements…

Multi-agent systems (MASs) have emerged as a promising paradigm for automated code generation, demonstrating impressive performance on established benchmarks. Despite their prosperous development, the fundamental mechanisms underlying their…

With the recent emergence of revolutionary autonomous agentic systems, research community is witnessing a significant shift from traditional static, passive, and domain-specific AI agents toward more dynamic, proactive, and generalizable…

Communication between multiple language model (LM) agents has been shown to scale up the reasoning ability of LMs. While natural language has been the dominant medium for inter-LM communication, it is not obvious this should be the…

Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…

Multi-agent reinforcement learning (MARL) is crucial for AI systems that operate collaboratively in distributed and adversarial settings, particularly in multi-domain operations (MDO). A central challenge in cooperative MARL is determining…

LLM-based multi-agent systems (LLM-MAS), in which autonomous AI agents cooperate to solve tasks, are gaining increasing attention. For such systems to be deployed in society, agents must be able to establish cooperation and coordination…

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models…

Multi-agent systems (MAS) powered by LLMs promise adaptive, reasoning-driven enterprise workflows, yet granting agents autonomous control over tools, memory, and communication introduces attack surfaces absent from deterministic pipelines.…