Autonomous agents, tool use, and agentic systems
![[2602.00185] QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2602.00185: QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities
Abstract page for arXiv paper 2506.22653: URSA: The Universal Research and Scientific Agent
Abstract page for arXiv paper 2505.00472: UserCentrix: An Agentic Memory-augmented AI Framework for Smart Spaces
This paper explores the expressive power of Mixture-of-Experts (MoEs) in modeling complex tasks, demonstrating their efficiency in approx...
The paper presents XENON, an advanced agent for robust planning in Minecraft that utilizes experience-based knowledge correction to impro...
This paper presents a non-asymptotic analysis of the Sticky Track-and-Stop algorithm, extending its guarantees beyond asymptotic optimali...
The paper introduces AgentNoiseBench, a framework for evaluating the robustness of tool-using LLM agents under noisy conditions, highligh...
PLAICraft introduces a large-scale dataset capturing time-aligned vision, speech, and action data from multiplayer Minecraft, aimed at ad...
This article explores the role of entropy in optimizing tool-use behaviors for Large Language Model (LLM) agents, highlighting the correl...
The paper presents ReaCritic, a novel reasoning transformer-based critic model for deep reinforcement learning (DRL) in heterogeneous wir...
The paper presents SEISMO, a trajectory-aware LLM agent designed to enhance sample efficiency in molecular optimization, achieving signif...
DIAGPaper introduces a multi-agent framework for identifying and prioritizing weaknesses in scientific papers, addressing limitations of ...
CaveAgent introduces a novel framework that transforms LLMs into stateful runtime operators, enhancing their ability to manage complex ta...
The paper presents Earth AI, a novel approach to geospatial analysis using foundation models and cross-modal reasoning to derive insights...
The paper explores continual learning (CL) in AI, proposing a shift from minimizing memory usage to leveraging abundant memory while addr...
This article presents a computational model that explores how humans and AI can integrate linguistic guidance and direct experience for e...
The paper presents an Amortized Bayesian Workflow that combines fast amortized inference with accurate MCMC techniques, optimizing Bayesi...
This paper presents novel domain adaptation methods for Spiking Neural Networks (SNNs) to address performance drops due to mismatched tem...
The paper presents evaluation methods for assessing the economic decision-making capabilities of LLMs, focusing on benchmarks and litmus ...
The article presents SurgRAW, a multi-agent workflow utilizing Chain of Thought reasoning for enhanced robotic surgical video analysis, a...
The article presents PCAS, a Policy Compiler designed to enforce complex authorization policies in LLM-based agents, improving compliance...
The paper presents a framework called Calibrate-Then-Act (CTA) that enables LLMs to optimize decision-making by balancing cost and uncert...
The SPARC framework enhances automated C unit test generation by bridging the gap between program intent and syntactic constraints, impro...
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime