AgentRivet: LLM-Based System Automates Creation of Particle Physics Analysis Routines
Researchers developed AgentRivet, an automated workflow using large language models to generate Rivet routines—C++ code used in particle physics experiments—from published journal articles. Currently only 39% of particle physics measurements have publicly available Rivet routines, creating a significant gap in analysis preservation. The system demonstrates that LLMs can produce functional routines with reasonable physics fidelity, though implementation challenges remain due to ambiguous publication definitions.
AgentRivet is an automated system that uses large language models from OpenAI, Anthropic, and Google to extract physics analysis information from published papers and generate missing Rivet routines. Rivet is a C++ toolkit essential for particle physics collider experiments, enabling theoretical models to be compared against measurements and supporting the development of Monte Carlo event generators and searches for physics beyond the Standard Model. The workflow incorporates intermediate code and physics reviews as autonomous quality control measures. Testing on two recent measurements from ATLAS and CMS experiments showed that AgentRivet produces competent routines with minimal syntax errors and reasonable physics fidelity that generally aligns with published explanations. However, physics implementation issues do arise, primarily stemming from subtle ambiguities in publication definitions, with some models struggling to implement complex observables even when clear specifications are provided.
What's missing
The study does not provide detailed quantitative metrics comparing performance across the three LLM providers (OpenAI, Anthropic, Google), nor does it specify the exact nature or frequency of physics implementation issues encountered, which would be valuable for assessing practical deployment readiness.
What different sources said
- arXiv cs.AICenter
AgentRivet: an automated system for producing Rivet routines from journal publications
Related
Topology-Aware Thermodynamics Improves DNA Probe Specificity Design
Researchers developed a new framework for designing DNA probes that accounts for the spatial organization of matched sequences, not just overall thermodynamic stability. Traditional methods rely on scalar measures like melting temperature and free energy, which miss how mismatches are distributed along the probe. The approach could improve diagnostic accuracy in applications like HPV detection and gene expression profiling.
Study Identifies Optimal Thermal Dose for Combining Focused Ultrasound with Immunotherapy in Tumors
Researchers used multimodal PET imaging to identify an optimal thermal dose range for focused ultrasound ablation that destroys tumor tissue while preserving conditions for immunotherapy delivery. The study found that excessive heating collapses blood vessels needed for antibody access, while insufficient heating fails to adequately reduce tumor burden. The findings could guide clinical design of combination treatments pairing thermal ablation with immunotherapies.
Plant MSH1 Protein Functions as Mismatch-Directed Nuclease for Organelle Genome Maintenance
Researchers have identified the precise mechanism by which the AtMSH1 protein in Arabidopsis plants recognizes and cleaves DNA mismatches and lesions, preventing mutations in organellar genomes. The protein combines a DNA mismatch recognition module with a nuclease domain that makes staggered cuts at specific positions relative to DNA damage. This discovery explains how plants maintain unusually low mutation rates in their mitochondrial and chloroplast DNA compared to other eukaryotes.