Autonomous agents, tool use, and agentic systems
![[2603.16663] When Openclaw Agents Learn from Each Other: Insights from Emergent AI Agent Communities for Human-AI Partnership in Education](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2603.16663: When Openclaw Agents Learn from Each Other: Insights from Emergent AI Agent Communities for Hum...
Abstract page for arXiv paper 2601.13508: Autonomous Computational Catalysis Research via Agentic Systems
Abstract page for arXiv paper 2512.08980: Training Multi-Image Vision Agents via End2End Reinforcement Learning
The paper explores using Perlin noise as a coordinator for AI in large-scale game environments, addressing challenges in balancing behavi...
This article explores the geometric analysis of multi-task grokking in machine learning, detailing five key phenomena observed during tra...
The paper introduces High-Dimensional Procedural Content Generation (HDPCG), a framework that enhances gameplay mechanics by treating non...
The paper presents DREAM, a framework for evaluating Deep Research Agents, addressing challenges in assessing research quality through ag...
The paper introduces TPRU, a dataset aimed at improving temporal and procedural understanding in Multimodal Large Language Models (MLLMs)...
The paper introduces ABD, a benchmark for default-exception abduction in finite first-order worlds, evaluating LLMs on their ability to d...
The paper presents the Unified Memory Agent (UMA), an end-to-end reinforcement learning framework designed for long-context reasoning, en...
The paper presents GenPlanner, a novel approach to path planning in complex environments using generative models, specifically diffusion ...
The LAMMI-Pathology framework proposes a novel tool-centric approach for enhancing molecularly informed medical intelligence in pathology...
This paper discusses the convergence of Schema-Guided Dialogue Systems and the Model Context Protocol, proposing five foundational princi...
The paper presents the LaDa framework, addressing the challenges of data allocation in federated learning by enhancing model learnability...
This article presents a novel framework for chart summarization using a multimodal agent approach, enhancing data accessibility and insig...
The paper presents TEB, a Task-aware Exploration approach that enhances exploration in visual reinforcement learning by utilizing a predi...
The paper explores how autonomous AI analysts using large language models can replicate diverse analytic outcomes on the same dataset, re...
The paper presents GEARS, a novel framework for optimizing large-scale ranking systems by transforming the optimization process into an a...
The paper discusses a novel approach to automated verification in CAS adaptation using vibe coding and feedback loops, demonstrating effe...
The paper presents Hierarchical Reward Design from Language (HRDL), a framework to align AI behavior with human specifications through en...
The paper discusses the limitations of viewing semantics as static in visual intelligence, proposing a dynamic framework that integrates ...
The article introduces ASKB, a new AI-driven feature for the Bloomberg Terminal, highlighting its potential to enhance user experience an...
Alipay's AI payment and health applications have each surpassed 100 million users, highlighting a significant trend in AI adoption among ...
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime