Related papers: Unifying Dynamic Tool Creation and Cross-Task Expe…

Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs. Many multimodal tasks, especially those involving…

Building state-of-the-art (SOTA) predictive models for drug discovery requires expensive search over tools, architectures, and training strategies. Current LLM-based agents can find SOTA solutions through extensive trial and error, but they…

We present APT, an advanced Large Language Model (LLM)-driven framework that enables autonomous agents to construct complex and creative structures within the Minecraft environment. Unlike previous approaches that primarily concentrate on…

Most LLM-based agent frameworks adopt a top-down philosophy: humans decompose tasks, define workflows, and assign agents to execute each step. While effective on benchmark-style tasks, such systems rely on designer updates and overlook…

The evolution of Large Language Models (LLMs) from passive text generators to autonomous, goal-driven systems represents a fundamental shift in artificial intelligence. This chapter examines the emergence of agentic AI systems that…

The statelessness of foundation models bottlenecks agentic systems' ability to continually learn, a core capability for long-horizon reasoning and adaptation. To address this limitation, agentic systems commonly incorporate memory modules…

Recent advancements in large language models (LLMs) have brought significant changes to various domains, especially through LLM-driven autonomous agents. A representative scenario is in software development, where LLM agents demonstrate…

Long-term multi-agent systems inevitably generate vast amounts of trajectories and historical interactions, which makes efficient memory management essential for both performance and scalability. Existing methods typically depend on vector…

Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to Tool Overuse, where models…

Distributed AI systems face critical memory management challenges across computation, communication, and deployment layers. RRAM based in memory computing suffers from scalability limitations due to device non idealities and fixed array…

Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entries and retrieve them only by semantic similarity. This leads to two key challenges for…

While large language models (LLMs) have advanced the development of general-purpose agents, achieving robust generalization to unseen tasks remains a significant challenge. Current approaches typically rely on either fine-tuning or…

Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowledge of once-learned environments sans catastrophic…

Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory…

Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents. A representative scenario is in software development, where agents can collaborate in a team like humans,…

Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individuals. Different civilizations developed different political…

Language agents have shown promising adaptability in dynamic environments to perform complex tasks. However, despite the versatile knowledge embedded in large language models, these agents still fall short when it comes to tasks that…

While Large Language Models (LLMs) excel at generalized reasoning, standard retrieval-augmented approaches fail to address the disconnected nature of long-term agentic memory. To bridge this gap, we introduce Synapse (Synergistic…

LLM-powered embodied agents have shown success on conventional object-rearrangement tasks, but providing personalized assistance that leverages user-specific knowledge from past interactions presents new challenges. We investigate these…

Tool learning is increasingly important for large language models (LLMs) to effectively coordinate and utilize a diverse set of tools in order to solve complex real-world tasks. By selecting and integrating appropriate tools, LLMs extend…