Add Agon, AutoNumerics, and AutoResearch Survey

README.md

@@ -108,6 +108,10 @@ $^*$ Ecological validity refers to how well the results of a study can be applie
 
 - **GIS Copilot (Akinboyewa et al., 2024)**: A framework that integrates Large Language Models (LLMs) into existing Geographic Information System (GIS) platforms, exemplified by QGIS, to autonomously generate spatial analysis workflows and code, thereby enabling users to perform spatial analyses through natural language commands. 
 
+- **Agon (Sun et al., 2026)**: Treats prompt engineering as an engineering discipline, minimizing human time while expecting maximum output across the full research loop. Carries the smallest prompt footprint among cross-disciplinary autoresearch systems (18 roles, 230.6 KiB total) and has run across 10+ scientific fields without modification. [Paper](https://arxiv.org/abs/2606.24177) [Code](https://github.com/AutoResearch-Factory/Agon)
+
+- **AutoNumerics (Du et al., 2026)**: Takes a PDE problem stated in plain text and produces a working numerical solver end-to-end, choosing the right discretization scheme (Fourier spectral, Chebyshev, etc.) based on the equation's structure. Geometric mean nRMSE on CodePDE is 9e-9, about six orders of magnitude below neural baselines. [Paper](https://arxiv.org/abs/2602.17607) [Code](https://github.com/Daviddjddu/Autonumerics)
+
 ### Task-Specific Agents
 - **VirSci (Su et al., 2024)**: A large language model-based multi-agent system that emulates collaborative scientific research to enhance the generation of novel and impactful scientific ideas.
 
@@ -128,12 +132,17 @@ $^*$ Ecological validity refers to how well the results of a study can be applie
 - **Morris (2023)**: The paper examines scientists' views on how generative AI could enhance various aspects of their work, including research, education, and communication, while also addressing potential concerns.
 
 
+- **Sun et al. (2026)**: Maps 56 autonomous research systems onto seven axes (loop topology, verifier gate scope, orchestration mode, portfolio parallelism, artifact substrate, disciplinary coverage, lifecycle coverage). The main finding: most systems can generate research artifacts, but almost none gate publication on verified correctness. [Project Page](https://haizhaoyang.github.io/research/autoresearch-survey.html)
+
+
 ## Full Bibliography
 
 - Temitope Akinboyewa, Zhenlong Li, Huan Ning, M. Naser Lessani. 2024. **GIS Copilot: Towards an Autonomous GIS Agent for Spatial Analysis**. In *arXiv*. https://arxiv.org/abs/2411.03205 
 
 - Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, Sung Ju Hwang. 2024. **ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models**. In *arXiv*. https://arxiv.org/abs/2404.07738 
 
+- Jianda Du, Youran Sun, Haizhao Yang. 2026. **AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing**. In *arXiv*. https://arxiv.org/abs/2602.17607
+
 - Daniil A. Boiko, Robert MacKnight, Gabe Gomes. 2023. **Autonomous chemical research with large language models**. In *Nature*. https://doi.org/10.1038/s41586-023-06792-0
 
 - Andres M. Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D. White, Philippe Schwaller. 2024. **Augmenting large language models with chemistry tools**. In *Nat Mach Intell*. https://doi.org/10.1038/s42256-024-00832-8 
@@ -190,12 +199,16 @@ $^*$ Ecological validity refers to how well the results of a study can be applie
 
 - Biqing Qi, Kaiyan Zhang, Haoxiang Li, Kai Tian, Sihang Zeng, Zhang-Ren Chen, Jin-Fang Hu, Bowen Zhou. 2023. **Large Language Models are Zero Shot Hypothesis Proposers**. In *Instruction Workshop @ NeurIPS 2023*. https://arxiv.org/abs/2311.05965
 
+- Xingyu Ren, Youran Sun, Chugang Yi, Kejia Zhang, Jiaxuan Guo, Jianda Du, Haizhao Yang. 2026. **What's Missing in Autonomous Research? A Systematization of Systems, Benchmarks, and Verification**. https://haizhaoyang.github.io/research/autoresearch-survey.html
+
 - Yusuf Roohani, Andrew Lee, Qian Huang, Jian Vora, Zachary Steinhart, Kexin Huang, Alexander Marson, Percy Liang, Jure Leskovec. 2024. **BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments**. In *arXiv*. https://arxiv.org/abs/2405.17631
 
 - Chenglei Si, Diyi Yang, Tatsunori Hashimoto. 2024. **Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers**. In *arXiv*. https://arxiv.org/abs/2409.04109
 
 - Michael D. Skarlinski, Sam Cox, Jon M. Laurent, James D. Braza, Michaela Hinks, Michael J. Hammerling, Manvitha Ponnapati, Samuel G. Rodriques, Andrew D. White. 2024. **Language agents achieve superhuman synthesis of scientific knowledge**. In *arXiv*. https://arxiv.org/abs/2409.13740 
 
+- Youran Sun, Xingyu Ren, Chugang Yi, Jiaxuan Guo, Kejia Zhang, Jianda Du, Haizhao Yang. 2026. **Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy**. In *arXiv*. https://arxiv.org/abs/2606.24177
+
 - Haoyang Su, Renqi Chen, Shixiang Tang, Xinzhe Zheng, Jingzhe Li, Zhenfei Yin, Wanli Ouyang, Nanqing Dong. 2024. **Two Heads Are Better Than One: A Multi-Agent System Has the Potential to Improve Scientific Idea Generation**. In *arXiv*. https://arxiv.org/abs/2410.09403
 
 - Zechang Sun, Yuan-Sen Ting, Yaobo Liang, Nan Duan, Song Huang, and Zheng Cai. 2024. **Interpreting Multi-band Galaxy Observations with Large Language Model-Based Agents**. In *arXiv*. https://arxiv.org/abs/2409.14807