PhysicsarXiv
Heuristic editor, no API keyVerdict: Notabletextbf textsc HepUKE : Uncertainty-aware Knowledge Evolution for High Energy Physics Analysis Agents
Knowledge bases are essential to agents for high energy physics (HEP), supplying few-shot evidence for previously unseen tasks.
Key numbers
- 43.0 % while preserving most answer
- 14.5 % with a similar quality--efficiency
Caveats
- Preprint; not yet peer reviewed.
VerdictWorth a reader's time today.
Abstract
Knowledge bases are essential to agents for high energy physics (HEP), supplying few-shot evidence for previously unseen tasks. Their principal utility lies in strategic guidance for novel analyses rather than ready-made answers or reusable code. Prevailing systems, however, treat all retrieved evidence as equally trustworthy and fail to accrue knowledge from the analyses under assistance. In this paper, inspired by the standard HEP treatment of uncertainty, we propose HepUKE: an Uncertainty-aware Knowledge Evolution system for HEP that repurposes information entropy to unify statistical uncertainty from LLM generation and systematic uncertainty from HEP methodological choices. Upon it, we construct a self-evolving domain-specific-language (DSL) knowledge base and release a large-scale expert-annotated HEP physics-analysis benchmark. Per-evidence confidence is quantified via the information entropy of sampled DSL generations: high-confidence precedents constrain program synthesis, whereas analyses lacking close precedents are validated and written back, sustaining continual knowledge evolution. To handle the highly redundant yet logically stringent nature of HEP knowledge, we introduce an early-stopping controller that fuses a backward stationarity test on the answer posterior with a forward marginal information gain estimate. On the 1,000-pair BESIII PhysicsQA benchmark, HepUKE reduces retrieval rounds by 43.0% while preserving most answer quality, and on the out-of-domain HotpotQA benchmark, it reduces retrieval rounds by 14.5% with a similar quality--efficiency trade-off. The code and datasets used in this work are available at https://anonymous.4open.science/r/HepUKE-32FF.
The editor's rubric
| Dimension | Level | Weight | What that level means |
|---|---|---|---|
| Leverage | ████░ 4 | 18% | A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing). |
| Magnitude | ███░░ 3 | 20% | Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem. |
| Evidence | ███░░ 3 | 22% | Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data. |
| Novelty | ███░░ 3 | 22% | A genuinely new approach to an open problem. |
| Trajectory | ███░░ 3 | 10% | A clear path to scale. |
| Stakes | ██░░░ 2 | 8% | Benefits a professional community (practitioners, clinicians, engineers). |
Editor’s rationale
Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); breadth (zero/few-shot); gains (relative gain); novelty (alternative to status quo); verification (error bars, held-out test, experimental validation); scale (scalable, efficient); stakes (energy).
How the score was computed
- Merit
- 6.2 / 10
- Adjusted merit
- 5.1 / 10
- Attention
- 0%
- Freshness
- 73%
- Citations0 (reference 20, via semantic-scholar, Oct 12, 2026, 07:25 UTC)