*** To appear in IJCAI 2015 proceedings *** In Constraint Programming (CP), a portfolio solver uses a variety of different solvers for solving a given Constraint Satisfaction / Optimization Problem. In this paper we introduce sunny-cp2: the first parallel CP portfolio solver that enables a dynamic, cooperative, and simultaneous execution of its solvers in a multicore setting. It incorporates state-of-the-art solvers, providing also a usable and configurable framework. Empirical results are very promising. sunny-cp2 can even outperform the performance of the oracle solver which always selects the best solver of the portfolio for a given problem.
A Review of Literature on Parallel Constraint Solving
School of Computer Science University of St Andrews（圣安德鲁斯大学计算机科学学院）；School of Computing Science University of Glasgow（格拉斯哥大学计算科学学院）；Adobe Systems Incorporated（Adobe系统公司）
The University of Melbourne（墨尔本大学）；University of Bologna（博洛尼亚大学）；INRIA（法国国家信息与自动化研究所）；University of Oslo（奥斯陆大学）
在约束编程（CP）中，投资组合求解器结合了各种不同的约束求解器来解决给定的问题。这种相当新的方法能够显着提高单求解器的性能，特别是在利用多核架构时。在这项工作中，我们简要介绍了投资组合求解器sunny-cp，并讨论了它在MiniZinc挑战赛中的表现--这是CP求解器的年度国际竞赛--在2015年和2016年赢得了两枚金牌。逻辑程序设计理论与实践（Theory and Practice of Logic Programming，TPLP）
ChemToolAgent: The Impact of Tools on Language Agents for Chemistry Problem Solving
Department of Computer Science and Engineering, OSU（计算机科学与工程系，俄勒冈州立大学）；Department of Biomedical Informatics, OSU（生物医学信息学系，俄勒冈州立大学）；College of Pharmacy, OSU（药学院，俄勒冈州立大学）
Mojo: A Promising Tool for Scalable Financial AI Efficiency
Data Science and Artificial Intelligence Innovation Laboratory, School of Engineering and Computer Science, Baylor University（贝勒大学工程与计算机科学学院数据科学与人工智能创新实验室）
Towards Human-Like Automated Test Generation: Perspectives from Cognition and Problem Solving
School of Innovation, Design and Engineering, Mälardalen University（梅拉达伦大学创新、设计与工程学院）；Department of Computer Science and Engineering, Chalmers University of Technology（查尔姆斯理工大学计算机科学与工程系）
Retrieval-Augmented Instruction Tuning for Automated Process Engineering Calculations : A Tool-Chaining Problem-Solving Framework with Attributable Reflection
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub
Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Shanghai Jiao Tong University（上海交通大学）
