AgentRivet: LLM-Based System Automates Creation of Particle Physics Analysis Routines
Researchers have developed AgentRivet, an automated multi-step workflow using large language models to generate Rivet routines — C++ code used to compare theoretical particle physics models against experimental measurements — directly from journal publications. The system addresses a significant gap in analysis preservation: only 39% of particle physics measurements currently have documented, publicly available Rivet routines. AgentRivet could accelerate the development and tuning of Monte Carlo event generators and broaden the search for physics beyond the Standard Model by filling this coverage deficit.
AgentRivet is an automated pipeline that leverages commercial LLMs from OpenAI, Anthropic, and Google to extract physics analysis information from published papers and produce the corresponding Rivet routines, which are C++ implementations used within the Rivet toolkit to enable model-independent comparisons between theoretical predictions and experimental data. The system incorporates intermediate code and physics review steps as part of an autonomous quality control mechanism. It was evaluated on two recent measurements from the ATLAS and CMS experiments at the Large Hadron Collider. Results show that AgentRivet generates routines with few syntax errors and reasonable physics fidelity that generally reflects the descriptions given in the source publications. However, physics-implementation issues do arise, most commonly stemming from subtle or ambiguous definitions in the publications themselves, though some models also struggle with complex observables even when definitions are clear. The work is co-submitted to the High Energy Physics – Experiment, Artificial Intelligence, and High Energy Physics – Phenomenology communities on arXiv, carrying report number MCNET-26-14.
What's missing
The paper does not yet report quantitative benchmarks comparing AgentRivet-generated routines against human-written ones in terms of physics accuracy (e.g., histogram agreement metrics), nor does it detail the computational cost or latency of the full pipeline. It is also unclear whether the system has been validated on a broader, statistically representative sample of measurements beyond the two ATLAS and CMS cases studied, leaving generalizability an open question.
What different sources said
- arXiv cs.AICenter
AgentRivet: an automated system for producing Rivet routines from journal publications
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.