LensDesigner is an autonomous agent framework that emulates expert opticians to tackle the complex, non‑convex problem of optical lens design. It uses a large lens library (LensLib100K) and optics‑aware retrieval to provide valid structural seeds, then iteratively improves through a curriculum agent that learns and reuses design heuristics. The system is evaluated on LensArena, a benchmark of 120 diverse optical tasks, where it outperforms existing baseline algorithms in success rate and optimization efficiency.
By Lei Sun, Haoran Liang, Dannong Xu, Yao Gao, Yuyu Geng, Jinjin Gu, Kaiwei Wang, Danda Pani Paudel, Luc Van Gool
AbsorbEvo is an agentic framework that autonomously designs microwave absorbers by translating natural‑language performance goals into full‑wave‑simulated designs. It combines language reasoning, physics‑based prediction, and historical feedback to guide a candidate evolution strategy, using a low‑cost predictive model to rank designs before simulation. In tests on AbsorbBench‑36, AbsorbEvo achieved a 79.17% task success rate, outperforming generic agents and random search.
By Zhicheng Feng, Yubo Zhao, Xuefeng Yao
Designing high-performance microwave absorbers requires specialized expertise in electromagnetic theory, materials science and simulation programming, and entails time-consuming optimization. Here, we...
arXiv:2605. 28390v2 Announce Type: replace Abstract: Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems.
By Xujun Li, Kehan Zheng, Mingyuan Zhao, Yize Geng, Jinfeng Zhou, Qi Zhu, Fei Mi, Lifeng Shang, Minlie Huang, Hongning Wang
arXiv:2607. 21971v1 Announce Type: new Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.
By Shujin Wu, Cheng Qian, Xiusi Chen, Heng Ji
The paper introduces a unified large language model workflow for modeling and inverse-design of metasurfaces across multiple families. By converting geometries, design parameters, and optical responses into a shared instruction‑following text format, the authors fine‑tune Gemma‑2‑9B on eight distinct metasurface families. Compared to single‑family models, the joint model predicts all families’ optical responses simultaneously and reduces mean‑squared error by an average of 56.5%.
"whyItMatters":"The approach demonstrates that a shared sequence‑based LLM interface can streamline cross‑family metasurface design, eliminating the need for separate surrogate architectures for each geometry class."
By Huanshu Zhang, Lei Kang, Yuyan Chen, Luxiang Wang, Zhaolong Cao, Douglas H. Werner
SPADE (Self-Play in Adaptive Synthetic Executable Environments) is a reinforcement‑learning framework where a single large language model acts as both an Environment Designer—creating executable, long‑horizon training environments—and a Reasoning Agent—learning to act within those environments. The framework uses a regret signal based on the difference between rewarded performance with and without privileged hints to guide the Designer toward environments that are challenging yet solvable. Experiments show that, when scaled to 30‑billion‑parameter models, SPADE outperforms fixed‑environment baselines by significant margins across math, science, code, and reasoning benchmarks, and improves tool‑use performance on BFCL‑v4 and ACEBench‑Agent.
whyItMatters":"By making environment design a learnable component, SPADE enables continuous self‑improvement and demonstrates that adaptive, self‑generated training environments can substantially boost language‑model performance across diverse tasks."
By Bo Liu, Simon Yu, Yiding Jiang, Ao Qu, Andrew Zhao, Zichen Liu, Junsu Kim, Zijian Zhou, Seungone Kim, Tongzheng Ren, Mickel Liu, Hanfei Yu, Zhaorun Chen, Weiyan Shi, Paul Pu Liang, Luke Zettlemoyer, Yejin Choi, Natasha Jaques
arXiv:2608.28638v1 Announce Type: new
Abstract: Agent skills are portable packages of instructions and resources an agent consults at deployment. Self-evolving them fails in two ways today. First, sk...
By Jiale Liu, Pinze Ren, Yuqi Xia, Huan Wang, Zhenlin Zhao, Siming Dong
arXiv:2606. 28279v1 Announce Type: cross Abstract: We present HORIZON, a self-evolving agent framework that treats hardware design as repository-level code evolution.
By Cunxi Yu, Chenhui Deng, Nathaniel Pinckney, Brucek Khailany
arXiv:2607. 23469v1 Announce Type: cross Abstract: Photonic-crystal surface-emitting lasers (PCSELs) can combine high-power operation with narrow-divergence surface emission, but optimizing coupled parameters requires costly full-wave simulations.
By Longying Wen, Feiyang Wu, Jinglin Yu, Chongxian Yuan, Renjie Li, Zhaoyu Zhang
arXiv:2603. 20667v2 Announce Type: replace-cross Abstract: Existing prompt-optimization techniques rely on local signals, causing poor generalization across tasks.
By Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan
arXiv:2606. 09663v1 Announce Type: new Abstract: Recursive self-design refers to AI-assisted modification of the mechanisms by which an AI system is built, evaluated, and improved.
By Dun Li, Jiatao Li, Hongzhi Li