PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments

2026-08-14 · Yuhao Zhan, Bingxiang He, Zecong Tang, Chaojun Xiao arxiv

Self-evolving agents improve future behavior from interaction experience, yet existing evaluations typically optimize under fixed execution conditions and do not test recovery after those conditions change. To address this gap, we introduce PACE-Bench (Physics Adaptation via Code Evolution), a simulator-grounded benchmark of 144 source-to-target adaptation pairs across six physics domains. Each pair links a source environment to a mutated target environment with the same goal and interface. A code-driven design that succeeds in the source fails in the target, where agents must iteratively adapt it into a working target design using diagnostic sandbox feedback within a limited attempt budget. We compare ten self-evolving methods from four paradigms. The benchmark remains far from saturated: Reflexion + Qwen3-14B succeeds on only 35.9\% of full-benchmark pairs, while GPT-5.5 solves 66.7\% of the Statics subset under the full budget. Together, these results show that simulator-grounded reflection is more reliable than unverified self-revision, while memory anchors agents to early designs and broad tree search explores without converging. Even revealing exact physical changes does not raise the performance ceiling, pointing to mechanism redesign rather than parameter inference as the central bottleneck. Data and code are available at https://github.com/thunlp/PACE-Bench.

📄 PDF Abstract BibTeX arXiv:2608.14441

Code (0)

등록된 구현이 없습니다.

Unsupervised Adaptation of 3D CT Foundation Models for 3D CBCT Segmentation

2026-08-27 · Gauthier Miralles, Loic Le Folgoc, Vincent Jugnon, Pietro Gori arxiv

Accurate 3D segmentation of cone-beam CT (CBCT) is critical for interventional and radiation therapy applications, yet it remains limited by two compounding challenges: the scarcity of annotated CBCT data and the large d…

Unsupervised Domain Adaptation Liver Segmentation

SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction

2025-08-18 · Sujit Roy, Dinesha V. Hegde, Johannes Schmude, Amy Lin 외 arxiv

This paper introduces a high resolution, machine learning-ready heliophysics dataset derived from NASA's Solar Dynamics Observatory (SDO), specifically designed to advance machine learning (ML) applications in solar phys…

Weather Forecasting

Benchmarking Scientific Machine Learning Models for Air Quality Data

2026-03-22 · Khawja Imran Masud, Venkata Sai Rahul Unnam, Sahara Ali arxiv

Accurate air quality index (AQI) forecasting is essential for the protecting public health in rapidly growing urban regions, and the practical model evaluation and selection are often challenged by the lack of rigorous, …

White-Box Neural Ensemble for Vehicular Plasticity: Quantifying the Efficiency Cost of Symbolic Auditability in Adaptive NMPC

2026-02-02 · Enzo Nicolas Spotorno, Matheus Wagner, Antonio Augusto Medeiros Frohlich arxiv

We present a white-box adaptive NMPC architecture that resolves vehicular plasticity (adaptation to varying operating regimes without retraining) by arbitrating among frozen, regime-specific neural specialists using a Mo…

Deepmechanics

2026-02-20 · Abhay Shinde, Aryan Amit Barsainyan, Jose Siguenza, Ankita Vaishnobi Bisoi 외 arxiv

Physics-informed deep learning models have emerged as powerful tools for learning dynamical systems. These models directly encode physical principles into network architectures. However, systematic benchmarking of these …