AI Agents & Automation

arXiv:2603.28731v1 Announce Type: cross Abstract: Modern distributed systems integrate heterogeneous services, REST APIs with different schema versions, GraphQL

arXiv:2603.28735v1 Announce Type: cross Abstract: AI-augmented ecosystems (interconnected systems where multiple AI components interact through shared data and

arXiv:2504.06188v2 Announce Type: replace Abstract: AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equip

arXiv:2507.17988v2 Announce Type: replace Abstract: Qualitative timeline-based planning models domains as sets of independent, but interacting, components whose

arXiv:2509.00761v3 Announce Type: replace Abstract: We present L-MARS (Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search), a multi-agent

arXiv:2510.08847v2 Announce Type: replace Abstract: We introduce the Agent GPA (Goal-Plan-Action) framework, driven by the fundamental insight that critical age

arXiv:2510.14035v2 Announce Type: replace Abstract: We introduce an uncertainty-aware graph representation framework for learning to guide planning in Partially

arXiv:2511.14043v3 Announce Type: replace Abstract: AI Scientific Assistant Core (AISAC) is a transparent, modular multi-agent runtime developed at Argonne Nati

arXiv:2512.08492v3 Announce Type: replace Abstract: Recent advances in Large Language Models have revolutionized function-level code generation; however, reposi

arXiv:2512.21782v2 Announce Type: replace Abstract: There has been unprecedented interest in developing agents that expand the boundary of scientific discovery,

arXiv:2603.04528v2 Announce Type: replace Abstract: Mathematical concepts emerge through an interplay of processes, including experimentation, efforts at proof,

arXiv:2603.06082v3 Announce Type: replace Abstract: Recent advances in deep learning inspired neural network-based approaches to computational materials discove

arXiv:2603.11382v4 Announce Type: replace Abstract: How can we determine whether an AI system preserves itself as a deeply held objective or merely as an instru

arXiv:2310.16472v4 Announce Type: replace-cross Abstract: We investigate semiring provenance--a successful framework originally defined in the relational databa

arXiv:2404.15390v3 Announce Type: replace-cross Abstract: Optimal computations under uncertainty require an adequate probabilistic representation about beliefs.

arXiv:2409.03166v3 Announce Type: replace-cross Abstract: Interactive robot learning is a challenging problem as the robot is present with human users who expec

arXiv:2410.09134v2 Announce Type: replace-cross Abstract: The need for autonomous and adaptive defense mechanisms has become paramount in the rapidly evolving l

arXiv:2410.21086v3 Announce Type: replace-cross Abstract: Road safety remains a critical challenge worldwide, with approximately 1.35 million fatalities annuall

arXiv:2501.08096v4 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has shown excellent performance in solving decision-making and control pro

arXiv:2505.04880v2 Announce Type: replace-cross Abstract: Understanding the high-level conceptual structure of quantum algorithms from their low-level circuit r

arXiv:2510.05145v2 Announce Type: replace-cross Abstract: Deep research agents, which synthesize information across diverse sources, are significantly constrain

arXiv:2510.06961v4 Announce Type: replace-cross Abstract: We present the Open ASR Leaderboard, a reproducible benchmarking platform with community contributions

arXiv:2510.09328v2 Announce Type: replace-cross Abstract: We study the problem of constructing Steiner Minimal Trees (SMTs) in hyperbolic space. Exact SMT compu

arXiv:2510.13044v2 Announce Type: replace-cross Abstract: Human motion is inherently diverse and semantically rich, while also shaped by the surrounding scene.

arXiv:2510.14884v2 Announce Type: replace-cross Abstract: In high-stakes AI applications, even a single action can cause irreparable damage. However, nearly all

arXiv:2510.16082v3 Announce Type: replace-cross Abstract: Interpreting gene clusters from RNA-seq remains challenging, especially in antimicrobial resistance st

arXiv:2510.16518v2 Announce Type: replace-cross Abstract: Advances in open-vocabulary semantic mapping and object navigation have enabled robots to perform an i

arXiv:2511.07014v2 Announce Type: replace-cross Abstract: Probabilistic forecasting is crucial in multivariate financial time-series for constructing efficient

arXiv:2511.07732v2 Announce Type: replace-cross Abstract: Can we turn a video prediction model into a robot policy? Videos, including those of humans or teleope

arXiv:2512.17396v2 Announce Type: replace-cross Abstract: In this work, we introduce RadImageNet-VQA, a large-scale dataset designed to advance radiologic visua

arXiv:2512.22065v2 Announce Type: replace-cross Abstract: Real-time, streaming interactive avatars represent a critical yet challenging goal in digital human re

arXiv:2601.00809v2 Announce Type: replace-cross Abstract: Agentic workflows driven by large language models (LLMs) are increasingly applied to Building Informat

arXiv:2601.04497v2 Announce Type: replace-cross Abstract: Modern forest monitoring workflows increasingly benefit from the growing availability of high-resoluti

arXiv:2601.11065v2 Announce Type: replace-cross Abstract: Fairness in automated decision-making has become a critical concern, particularly in high-pressure hea

arXiv:2601.15109v3 Announce Type: replace-cross Abstract: Interoperable data and intelligence flows among allied partners and operational end-users remain essen

arXiv:2601.20404v2 Announce Type: replace-cross Abstract: AI coding agents such as Codex and Claude Code are increasingly used to autonomously contribute to sof

arXiv:2602.04361v2 Announce Type: replace-cross Abstract: Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale

arXiv:2602.14477v2 Announce Type: replace-cross Abstract: Peer learning, where learners teach and learn from each other, is foundational to educational practice

arXiv:2602.20168v2 Announce Type: replace-cross Abstract: Emergency triage decisions are made under severe information constraints, yet most data-driven deterio

arXiv:2602.20323v4 Announce Type: replace-cross Abstract: Reliable object manipulation requires understanding physical properties that vary across objects and e

arXiv:2603.02190v2 Announce Type: replace-cross Abstract: We present Sketch2Colab, which turns storyboard-style 2D sketches into coherent, object-aware 3D multi

arXiv:2603.09455v2 Announce Type: replace-cross Abstract: Scenario-based testing is a key method for cost-effective and safe validation of autonomous vehicles (

arXiv:2603.10281v2 Announce Type: replace-cross Abstract: While score-based generative models have emerged as powerful priors for solving inverse problems, dire

arXiv:2603.13846v3 Announce Type: replace-cross Abstract: Advances in machine learning have enabled the creation of realistic synthetic videos known as deepfake

Use semantic search and RAG in C# with the Weaviate Managed .NET client — attribute-driven schema, type-safe queries, and safe migrations, all in idiomatic .NET

The 3-month gap between building an AI agent and it being useful nearly broke me. The early failures are the visible ones, but the deep problems only appear whe

AI agents may be fast and unpredictable in their reasoning, but their actions are concrete—and that's a problem security already knows how to solve.

Unix permissions were built for humans. AI agents inherit them wholesale. The structural failure has a name — the confused deputy problem, coined in 1988 — and