cs.AINov 11, 2026

Reward-Driven Collider Physics Challenges for Self-Improving Agentic AI via Reinforcement Learning

Authors: Alexander Yue, Qibin Liu, Julia Gonski

Organizations: Stanford University 450 Jane Stanford Way, Stanford, CA 94305 · SLAC National Accelerator Laboratory Menlo Park, CA 94025

Abstract

Recent advances in agentic AI have demonstrated the potential to automate complex high-energy physics (HEP) workflows. We focus on the regime of HEP tasks where frontier models still struggle to provide correct and complete solutions, and introduce an open-ended optimization task format with continuous, automatically evaluated rewards. Unlike conventional benchmarks focused on task completion, these tasks target reinforcement learning (RL) environments to generate agentic improvement on state- of-the-art HEP challenges. We benchmark frontier reasoning models on several HEP tasks and demonstrate an initial proof of concept in which a small language model improves through RL using automated feedback without human intervention. By connecting challenging HEP problems with verifiable scientific rewards and RL, we aim to advance agentic AI from reproducing established workflows to autonomously discovering better scientific solutions, paving the way toward self-improving scientific agents.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction

    May 13, 2026Darius A. Faroughy, Sofia Palacios Schweitzer, Ian Pang +2AI Agents for Scientific DiscoveryAI Agent Evaluation

  2. CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning

    Jan 21, 2026Tianshi Xu, Yuteng Chen, Meng LiAgentic RLReinforcement Learning