Aug 2026· Computer· Vol 59, pp. 28-38· 0 citations· 18 references
Computer Science
Abstract
The command-line interface evolves as LLM-based agentic systems add tool execution, planning, and persistent state, enabling autonomous multistep tasks while introducing new security risks today. This article synthesizes empirical evidence on productivity effects, examines current implementations, and provides practitioners with concrete guidance for safe adoption.
This seminar explores how frontier AI systems can be organized into specialized research 'teams' or multiple-agent workflows that support orchestrated literature review, analysis, synthesis, writing, and verification all under human control. It combines conceptual depth with practical demonstrations to help researchers...
This workshop explores how autonomous AI agents can support scientific research in R, from conceptual distinctions between chat systems and agentic workflows to practical deployment with open-source tools (OpenCode). It is designed for researchers who want to use AI critically, securely, and effectively in data-intensi...
This seminar explores how agentic AI can be integrated into academic research as a disciplined, verifiable, and human-led method rather than a generic productivity tool. It provides practical frameworks for responsible use, workflow verification, and multi-agent research design across literature work, analysis, writing...
The model abstracts how agents coordinate and co-regulate their cognitive cycles, providing a basis for analysing distributed cognition and designing cognitively interoperable human-AI systems.
Kolitha Kottagaha W.M, J.A.C. Bokhorst, B. Gaffinet et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
