Newest papers

TRACE: Governing AI-Assisted Research with Principles from Computer Science

Amirhossein Zohrehvand, Aldona Kapacinskaite · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.24035 · cited by 0 works (OpenAlex) · open-access PDF

French

L'intelligence artificielle (IA) rend plus facile que jamais de produire des résultats de recherche. La question pressante est de savoir comment les chercheurs devraient organiser leur travail avec cette technologie. La question n'est pas nouvelle: l'ingénierie logicielle et la recherche en sécurité ont longtemps étudié comment les équipes de personnes et de machines gardent le contrôle d'un corps de travail partagé avec de nombreux contributeurs. Nous distillons des principes à partir des pratiques que ces littératures rapportent et les transposent à la recherche assistée par l'IA. Les principes forment TRACE: Track records, Review against sources, Accept independently conversation, Control transitions, and Evaluate corrections. Together, les cinq principes fournissent aux chercheurs une base commune pour rester en contrôle tout en intégrant l'IA dans leurs flux

Machine translation (Meta M2M100); the English original follows.

Abstract

Artificial intelligence (AI) makes it easier than ever to produce research outputs. The pressing question is how researchers should organize their work with this technology. The question is not new: software engineering and security research have long studied how teams of people and machines keep control of a shared body of work with many contributors. We distil principles from the practices these literatures report and transpose them to AI-assisted research. The principles form TRACE: Track records, Review against sources, Accept independently, Control transitions, and Evaluate corrections. Together, the five principles give researchers a common basis for remaining in control while integrating AI into their workflows. By bounding units of work and attending to how each is shaped, they help researchers pace AI-assisted work to human attention rather than to the speed at which AI produces content. We also introduce TRACE-OS, an open source operating system for AI-assisted research projects. It puts the principles into practice through shared instructions, tools, and records that fit researchers' existing workflows. The shared standard can contribute to building trust, which allows teams to delegate and realize the productivity that AI promises. More broadly, we aim to open a conversation about the governing principles through which the research community can benefit from AI.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Delegate, Work (physics), Control (management), Computer science, Conversation, Pace

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange