arXiv:2606.13535v1 Announce Type: cross Abstract: Particle physics collider experiments provide Rivet routines as part of the analysis preservation strategy for model-independent measurements. Rivet is a C++ toolkit that allow new theoretical models to be compared to the measurements, thus aiding the development and tuning of Monte Carlo event generators as well as searches for physics beyond the Standard Model. However, analysis coverage is known to be incomplete, with only 39% of measurements having documented and publicly available Rivet routines. In this article, we design and implement an
The development of AgentRivet reflects the increasing application of AI and agentic systems to automate complex scientific and analytical tasks, addressing current bottlenecks in research preservation and accessibility.
This development represents a significant step towards automating knowledge extraction and code generation directly from scientific publications, enhancing the efficiency of scientific discovery and data utilization across fields.
The process of creating and maintaining Rivet routines for particle physics measurements, which was previously manual and incomplete, can now be largely automated, leading to more comprehensive and accessible scientific data.
- · Particle physicists
- · High-energy physics research institutions
- · AI agent developers
- · Monte Carlo event generator developers
- · Manual data curators
- · Inefficient analysis preservation strategies
Increased availability and consistency of Rivet routines for new theoretical models in particle physics.
Faster validation and tuning of new theoretical models against experimental data, accelerating scientific progress.
The methodology could be generalized to automate knowledge extraction and code generation from publications in other scientific domains, revolutionizing research workflows.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI