Related papers: SkillOS: Learning Skill Curation for Self-Evolving…

Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not…

Skill Incremental Learning (SIL) is the process by which an embodied agent expands and refines its skill set over time by leveraging experience gained through interaction with its environment or by the integration of additional data. SIL…

The success of today's AI applications requires not only model training (Model-centric) but also data engineering (Data-centric). In data-centric AI, active learning (AL) plays a vital role, but current AL tools 1) require users to manually…

Large Language Model (LLM) agents are increasingly extended at runtime via skill packages, structured natural-language instruction bundles loaded from a well-known directory. Community install tooling and registries exist, but two gaps…

Intelligent agents rely heavily on prior experience when learning a new task, yet most modern reinforcement learning (RL) approaches learn every task from scratch. One approach for leveraging prior knowledge is to transfer skills learned on…

Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge through post-hoc credit…

Open-ended AI agents need to be able to learn efficiently goals of increasing complexity, abstraction and heterogeneity over their lifetime. Beyond sampling efficiently their own goals, autotelic agents specifically need to be able to keep…

Reinforcement learning (RL) has emerged as a viable recipe for training LLM agents to reason over external memory banks in multi-session dialogue. Existing work trains exclusively on a single benchmark, leaving open how the composition of…

Reinforcement learning (RL) trains agents to accomplish complex tasks through environmental interaction data, but its capacity is also limited by the scope of the available data. To obtain a knowledgeable agent, a promising approach is to…

Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a…

Autonomous graphical user interface (GUI) agents powered by multimodal large language models have shown great promise. However, a critical yet underexplored issue persists: over-execution, where the agent executes tasks in a fully…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

Large language model (LLM)--based agents have emerged as pivotal tools in assisting human experts across various fields by transforming complex tasks into more efficient workflows and providing actionable stakeholder insights. Despite their…

Long-horizon contact-rich bimanual manipulation presents a significant challenge, requiring complex coordination involving a mixture of parallel execution and sequential collaboration between arms. In this paper, we introduce a hierarchical…

Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with long-horizon workflows. A key bottleneck is the grounding gap in existing skill formulations:…

Lifelong learning offers a promising paradigm of building a generalist agent that learns and adapts over its lifespan. Unlike traditional lifelong learning problems in image and text domains, which primarily involve the transfer of…

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a…

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…

Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fail to capture quality differences among trajectories…

One of the final frontiers in the development of complex human - AI collaborative systems is the ability of AI agents to comprehend the natural language and perform tasks accordingly. However, training efficient Reinforcement Learning (RL)…