2.8 KiB
2.8 KiB
tags:: #todoist-task PAPERS date:: 09-12-2025 - 11:27 progress:: {{renderer :todomaster}}
- ### Tasks
- DONE Figura 1 va rifatta per evitare problemi di Copyright
id:: 6938230f-5522-4dfe-97b1-3b4b45b243bc
- DONE Prendere Fig. 8 del deliverable
id:: 693824d3-dc99-4446-b3f6-b4f8138369be
- DONE Capire come gestire i riferimenti di tabella 1, quindi se avere o meno una sezione appendix
id:: 69346801-0c02-4688-9eec-1f87ed6f3d55
- DONE Forse da aggiungere un esempio/dettaglio in una delle 5 dimensioni
id:: 693830c2-f57a-4ab4-9608-5809534ed345
:LOGBOOK:
CLOCK: [2026-01-02 Fri 23:17:19]--[2026-01-02 Fri 23:17:20] => 00:00:01
:END:
- DONE Sfruttare quando possibile i footnote invece delle ref (limitate a 15)
-
- ### Notes
- This is a paper to be submitted to the IEEE Special issue [Call for Papers: Special Issue on Engineering Agentic Systems](https://www.computer.org/digital-library/magazines/so/cfp-engineering-agentic-systems)
- The issue is seeking submissions meeting the following requests:
- Developers must **decide whether to rely on the FM/LLM or external tools/systems for the same functionality**. These decisions can be made at various stages depending on the problem and context: during design time, development time, or event at runtime from a software engineering perspective, and at pre-training time, post-training time, test/inference time, and post-inference time from an AI perspective. Highly autonomous agentic systems also require continuous monitoring, evaluation, observability, intervention, and oversight after deployment, an emerging discipline referred to as AgentOps. Designing this post-deployment environment is also highly complex, with many interdependent design choices.
- This special issue aims to address these challenges by **exploring cutting-edge engineering methods, techniques, tools, and practices for agentic systems.** It seeks articles that provide with **insights into the design, development, and operation of agentic systems**, emphasizing practical applications and **real-world experiences**.
- Topics of interests include, but are not limited to:
- Requirements engineering for agentic systems
- Architectural design for agentic systems
- Verification, validation, and testing of agentic systems
- AgentOps - DevOps for agentic systems
- Development processes and lifecycle management for agentic systems
- Evaluation methodologies, tools, and benchmarks for agentic systems
- Responsible AI and AI safety of agentic systems
- Agentic systems for software engineering, including requirements, design, coding, testing, deployment, and operations
- Human-agent interaction, collaboration, and oversight
- Risk and impact assessment (e.g. economic/social impact)
- Real-world case studies and practical experiences in different domain