Related papers: PolySkill: Learning Generalizable Skills Through P…

Large language model (LLM) powered AI agents have emerged as a promising paradigm for autonomous problem-solving, yet they continue to struggle with complex, multi-step real-world tasks that demand domain-specific procedural knowledge.…

A major driver of AI products today is the fact that new skills emerge in language models when their parameter set and training corpora are scaled up. This phenomenon is poorly understood, and a mechanistic explanation via mathematical…

Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…

As large language models (LLMs) become increasingly advanced, their ability to exhibit compositional generalization -- the capacity to combine learned skills in novel ways not encountered during training -- has garnered significant…

Large language models (LLMs) hold promise for generating plans for complex tasks, but their effectiveness is limited by sequential execution, lack of control flow models, and difficulties in skill retrieval. Addressing these issues is…

This search introduces the Multimodal Socialized Learning Framework (M-S2L), designed to foster emergent social intelligence in AI agents by integrating Multimodal Large Language Models (M-LLMs) with social learning mechanisms. The…

Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-driven capability sharing. However, despite their rapid…

This paper presents a novel approach to generalizing robot manipulation skills by combining a sampling-based task-and-motion planner with an offline reinforcement learning algorithm. Starting with a small library of scripted primitive…

Text-rich visual understanding-the ability to process environments where dense textual content is integrated with visuals-is crucial for multimodal large language models (MLLMs) to interact effectively with structured environments. To…

It is desirable for an agent to be able to solve a rich variety of problems that can be specified through language in the same environment. A popular approach towards obtaining such agents is to reuse skills learned in prior tasks to…

Competency modeling is widely used in human resource management to select, develop, and evaluate talent. However, traditional expert-driven approaches rely heavily on manual analysis of large volumes of interview transcripts, making them…

Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. They also, paradoxically, struggle with basic functionality, such as arithmetic or factual lookup,…

Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especially important in open-domain question answering, where broad or copied queries often…

We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…

Graphical User Interface (GUI) agents offer cross-platform solutions for automating complex digital tasks, with significant potential to transform productivity workflows. However, their performance is often constrained by the scarcity of…

This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation. DreamLLM operates on two…

Although most current large multimodal models (LMMs) can already understand photos of natural scenes and portraits, their understanding of abstract images, e.g., charts, maps, or layouts, and visual reasoning capabilities remains quite…

We conduct the first empirical study on using knowledge transfer to improve the generalization ability of large language models (LLMs) in software engineering tasks, which often require LLMs to generalize beyond their training data. Our…

Robots trained via Reinforcement Learning (RL) or Imitation Learning (IL) often adapt slowly to new tasks, whereas recent Large Language Models (LLMs) and Vision-Language Models (VLMs) promise knowledge-rich planning from minimal data.…

Modern Large Language Models (LLMs) exhibit impressive zero-shot and few-shot generalization capabilities across complex natural language tasks, enabling their widespread use as virtual assistants for diverse applications such as…