Life sciences · Preprint

Searching for New Physics with Reinforcement Learning

arXiv · September 9, 2026

Hypothesis-Generating Why this matters to you Expert discussion

Raises a question worth testing. It does not answer one.

AI Summary

This is a preprint describing a reinforcement learning algorithm designed to identify Standard Model Effective Field Theory operators that could explain observed particle physics anomalies. The authors demonstrate the method's ability to reproduce known results on the CDF W-mass anomaly and extend it to multiple anomalies simultaneously, but the work is computational and exploratory, offering no new empirical evidence about physics.

What was studied

Preprint. Intervention: Reinforcement learning algorithm applied to identify SMEFT operators explaining anomalies. Compared with: Known phenomenological results on CDF W-mass anomaly.

Key findings

RL method successfully reproduces known results on the CDF W-mass anomaly and improves upon them Method can identify SMEFT operators explaining multiple anomalies simultaneously, in situations the authors describe as 'far more complicated' Approach addresses the challenge of exploring the complete SMEFT operator space, which human phenomenological intuition typically does not

Safety

Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.

Who this may help

The source did not state who this applies to in practice.

Plain-language summary

This is a methodological proof-of-concept applying reinforcement learning to theoretical physics model selection; it demonstrates a computational technique rather than generating empirical evidence about nature.

Study design

As stated by the source record.

InterventionReinforcement learning algorithm applied to identify SMEFT operators explaining anomalies

ComparatorKnown phenomenological results on CDF W-mass anomaly

Caveats

This is a preprint and has not undergone peer review
No quantitative metrics (precision, recall, computational cost, or improvement magnitude over prior methods) are reported
Validation is limited to retrospective analysis of two known anomalies; no prospective prediction or novel physics discovery is demonstrated
Generalizability to future anomalies or broader SMEFT landscapes is not empirically tested

Evidence assessment

Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.

Study design

limited

Computational method paper without experimental design or empirical data collection.

Directness

limited

Tests RL on theoretical anomalies, not direct measurement of new physics.

Consistency

moderate

Method reproduces known results on CDF W-mass anomaly; validation limited to two scenarios.

Risk of bias

insufficient

No empirical study; bias assessment not applicable to computational validation.

Sample adequacy

insufficient

Not applicable; demonstrates technique on two published anomalies, not a population study.

What is missing. This record has no reported figures. That is a gap in the analysis, not a judgement about the study.

Source abstract

Finding new physics (NP) is the most important problem in particle physics today. Studying ``anomalies'', i.e., measurements of low-energy observables whose values disagree with the predictions of the Standard Model (SM), is a powerful search strategy. The SM Effective Field Theory (SMEFT) provides a general model-independent framework for parameterizing NP; it is natural to try to find the SMEFT operator(s) that can explain such anomalies. This is a challenging task because (i) the number of SMEFT operators is enormous, and (ii) at loop level there are very complicated correlations among the operators. Analyses by humans typically rely on phenomenological intuition to decide which operators are relevant. This is often biased and does not explore the complete SMEFT operator space. Interestingly, reinforcement learning (RL) techniques excel at tasks that require decision making to achieve their goals. In this paper, we introduce an RL method that can be used to find the SMEFT operators that explain any anomalies. We test it on the CDF $W$-mass anomaly, and show that it reproduces (and improves upon) known results. We then consider a far more complicated situation with multiple anomalies and show that, even here, this method is able to find the SMEFT operators that explain the data. Our RL method can therefore be used to efficiently search for NP at the level of SMEFT.

Follow from this

Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.

Jacky KumarDavid LondonMarianne Bouchard