High Energy Physics

Shi Qiu, Junyi Deng, Yiwei Deng et al.

This benchmark provides a rigorous, expert-validated test for evaluating AI agents' capability to autonomously reproduce scientific research, revealing systematic failures that must be addressed for progress in AI-driven science.

Nathaniel S. Woodward, Zhiqi Gao, Yurii Kvasiuk et al.

This work provides a foundation for developing domain-specific reasoning capabilities in small LLMs for theoretical physics, addressing the scarcity of verifiable training data.

Vasilis Niarchos, Constantinos Papageorgakis, Alexander G. Stapleton et al.

This work provides a controlled testbed for evaluating interaction structures in AI-driven scientific discovery, offering practical insights for researchers using LLMs in theoretical physics.

Zachary Bogorad, Ibrahim Elsharkawy, Yonatan Kahn et al.

For high-energy physicists, this provides interpretable and reliable generative models that respect physical conservation laws exactly, addressing a key limitation of approximate methods.

Oz Amram, Darius A. Faroughy, Tjarko Gerdes et al.

For researchers training large generative models for collider physics, this work provides the first empirical evidence that scaling laws for jet generation differ from language models, highlighting fundamental limits in data and compute scaling.

Justin Berman, Francois Charton, Andres Luna et al.

This work addresses a key bottleneck in high-precision calculations for particle and gravitational-wave physics, offering a practical improvement for multi-loop integral reduction.

Darius A. Faroughy, Sofia Palacios Schweitzer, Ian Pang et al.

This benchmark addresses the need for realistic, domain-specific evaluation of AI agents in scientific research, particularly for complex, long-horizon tasks.

Alexander Roman, Marco Knipfer, Jogi Suda Neto et al.

This work addresses fundamental quantum resource theory for researchers in quantum information, but it is incremental as it focuses on specific measures in a limited system.

Pahal D. Patel, Sanmay Ganguly

For high-energy physics researchers, this provides a comparative evaluation of XAI methods for graph-based jet taggers, though the approach is incremental as it applies existing methods to a specific domain.

Ethan Baker, Hongwan Liu, Siddharth Mishra-Sharma

For cosmologists studying CMB spectral distortions, this provides the first fully open-source code for such computations, though the scientific contribution is incremental.

Luigi Favaro, Andrea Giammanco, Claudius Krause

This work addresses the need for fast and accurate detector simulations in high-energy physics, showing that ViTs are robust and scalable across different detector geometries.

Judy Fox, Geoffrey Fox

For scientists and researchers, this work provides practical agentic AI systems that automate data curation and report generation, though the approach is incremental.

Gregor Krzmanc, Vinicius Mikuni, Benjamin Nachman et al.

This work demonstrates that particle physics foundation models can generalize across vastly different energy scales and detector technologies, enabling detector-agnostic inference for the particle physics community.

Sven Krippendorf, Joseph Tooby-Smith

This provides a correctness-first, reusable workflow for theoretical physicists to handle combinatorially difficult model-building problems with theorem-backed guarantees, though it is incremental as it builds on existing ITP methods in a specific domain.

Cheng Jiang, Sitian Qian, Kevin Pedro et al.

This work addresses the computational bottleneck of high-precision calorimeter simulation for current and future colliders by providing a faster, end-to-end generative model that maintains physics fidelity.

Nathan Benjamin, A. Liam Fitzpatrick, Wei Li et al.

This work addresses the challenge of identifying unknown CFTs in theoretical physics, particularly in a parameter range lacking known examples, though it is incremental as it builds on existing modular bootstrap methods with technical improvements.

Loukas Gouskos, Benedikt Maier

For high-energy physics analyses requiring jet tagging, this work shows that physics-motivated representations remain complementary to state-of-the-art transformers, enabling substantial improvements in specific boosted di-Higgs searches.

Karla Tame-Narvaez, Steven Gardiner, Aleksandra Ćiprijanović et al.

This work addresses the need for more precise nuclear interaction simulations in neutrino physics, though it is incremental as it builds on existing tuning methods with a machine learning approach.

Siddharth Mishra-Sharma, Tracy R. Slatyer, Yitian Sun et al.

This work provides a flexible, probabilistic framework for astrophysical gamma-ray analyses, addressing the long-standing GCE puzzle by accounting for a continuum of spatial morphologies.

Saurabh Rai, Sanmay Ganguly

For jet physics practitioners, this work demonstrates that mechanistic interpretability methods from NLP can uncover physically meaningful circuits in jet taggers, providing a new tool for understanding and validating deep learning models in high-energy physics.