Related papers: Ace-Skill: Bootstrapping Multimodal Agents with Pr…
Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to…
The integration of Large Language Models (LLMs) into life sciences has catalyzed the development of "AI Scientists." However, translating these theoretical capabilities into deployment-ready research environments exposes profound…
External knowledge has played a crucial role in the recent development of computer use agents. We identify a critical knowledge-execution gap: retrieved knowledge often fails to translate into effective real-world task execution. Our…
Knowledge distillation is a long-established technique for knowledge transfer, and has regained attention in the context of the recent emergence of large vision-language models (VLMs). However, vision-language knowledge distillation often…
Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places…
AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant ones, degrades performance. As community-driven skill repositories grow,…
The development of continual learning (CL) methods, which aim to learn new tasks in a sequential manner from the training data acquired continuously, has gained great attention in remote sensing (RS). The existing CL methods in RS, while…
Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter updates in the…
Class imbalance in machine learning poses a significant challenge, as skewed datasets often hinder performance on minority classes. Traditional oversampling techniques, which are commonly used to alleviate class imbalance, have several…
This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy for enhancing the adaptability and flexibility of AI agents through inter-task self-evolution. Unlike existing methods focused on intra-task learning, ICE…
Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation…
Artificial Intelligence (AI) significantly influences many fields, largely thanks to the vast amounts of high-quality data for machine learning models. The emphasis is now on a data-centric AI strategy, prioritizing data development over…
Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…
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:…
Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iteration knowledge as natural-language feedback, flat episodic…
Multi-agent reinforcement learning (MARL) is employed to develop autonomous agents that can learn to adopt cooperative or competitive strategies within complex environments. However, the linear increase in the number of agents leads to a…
We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as…
Deep clustering outperforms conventional clustering by mutually promoting representation learning and cluster assignment. However, most existing deep clustering methods suffer from two major drawbacks. First, most cluster assignment methods…
To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks. However, the inconsistent task distribution and heterogeneity is hard to be handled through a global sharing model…
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…