20 results for “Automation”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper introduces PHP-AIO, a protocol for quantifying unpriced systemic risks in automation decisions using a five-gate sequential decision protocol.
Plover is a plan-centric vision-based GUI automation system that externalizes task plans and replanning as inspectable artifacts, enabling explicit supervision and localized correction.
A study comparing three automation conditions of a Smart Medication Support system for older adults, finding that higher automation does not always lead to higher trust or acceptance.
Chunmin Xia, Jakub Harbaczewski, Nikhil Dsilva, Julie Raulin +2 more
This paper proposes a distributed architecture for automating and controlling multi-vendor, multi-layer IP over DWDM networks using SDN, enabling end-to-end service lifecycle automation and closed-loo…
Yikun Fu, Bowen Fu, Zhenyu Wu, Shuang Cheng +9 more
The paper presents MacAgentBench, a comprehensive macOS agent benchmark for evaluating computer use agents.
The paper proposes a new paradigm for LLM-based agents in regulated industries, called compliance-by-construction, which integrates symbolic structures into the agent's architecture.
Jiaru Bai, Yuchi Zhao, Han Hao, Miroslav Bogdanovic +3 more
The paper introduces the self-building laboratory (SBL), a system that designs, configures, and operates its own laboratory setup given a high-level scientific goal.
Embodied Intelligent Empowered Base Station
This paper proposes an automated method to generate complete PDDL planning problems directly from Asset Administration Shell (AAS) capability models, eliminating the need for specialized planning expe…
The paper presents an IoT-enabled smart home system using Raspberry Pi 5 and environmental sensors to automatically manage devices, achieving over 46% energy savings compared to always-on models.
This paper introduces and compares two frameworks for extracting disassembly instructions from unstructured information sources.
The paper introduces Policy-First Tooling, a model-agnostic permission layer that significantly enhances the safety and reliability of tool-orchestrated AI workflows by enforcing explicit constraints…
Automation-Exploit is a multi-agent LLM framework that enables adaptive offensive security by using a digital twin to safely test and execute high-risk memory-corruption exploits on live targets.
This paper explores the use of AI agents in robotic engineering and their impact on productivity.
Adel ElZemity, Budi Arief, Shujun Li, Calvin Brierley +5 more
The paper introduces APIOT, the first LLM framework capable of autonomously performing the full discovery, exploitation, patching, and verification cycle against bare-metal industrial OT devices.
The paper presents the first T-API-compliant reasoning and act loop for intent-driven, closed-loop agentic management in optical networks.