Collider-Bench is a new benchmark showing that current LLM agents cannot reliably reproduce LHC analyses at the level of a physicist-in-the-loop.
RECAST: Extending the Impact of Existing Analyses
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Searches for new physics by experimental collaborations represent a significant investment in time and resources. Often these searches are sensitive to a broader class of models than they were originally designed to test. We aim to extend the impact of existing searches through a technique we call 'recasting'. After considering several examples, which illustrate the issues and subtleties involved, we present RECAST, a framework designed to facilitate the usage of this technique.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A reweighting method creates model-agnostic likelihoods from histogram analyses, applied to Belle II B+ to K+ nu nubar data for WET constraints and light new physics searches.
citing papers explorer
-
Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
Collider-Bench is a new benchmark showing that current LLM agents cannot reliably reproduce LHC analyses at the level of a physicist-in-the-loop.
-
Accelerating Discovery: Model-Agnostic Likelihoods for the Reinterpretation of Particle Physics Results and their Application to the Belle II $B^{+}\to K^{+}\nu\bar{\nu}$ Measurement
A reweighting method creates model-agnostic likelihoods from histogram analyses, applied to Belle II B+ to K+ nu nubar data for WET constraints and light new physics searches.