Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability to efficiently solve problems for interactive use. The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability, followed by large-scale reinforcement learning to improve end-to-end coding performance through stronger reasoning, accurate multi-step execution, and coherence on long-horizon realistic coding problems. We develop infrastructure to support training in the same Cursor harness that is used by the deployed model, with equivalent tools and structure, and use environments that match real problems closely. To measure the ability of the model on increasingly difficult tasks, we introduce a benchmark derived from real software engineering problems in large codebases including our own. Composer 2 is a frontier-level coding model and demonstrates a process for training strong domain-specialized models. On our CursorBench evaluations the model achieves a major improvement in accuracy compared to previous Composer models (61.3). On public benchmarks the model scores 61.7 on Terminal-Bench and 73.7 on SWE-bench Multilingual in our harness, comparable to state-of-the-art systems.

翻译：Composer 2 是一款专为智能体软件工程设计的专用模型。该模型在保持高效交互式问题求解能力的同时，展现出强大的长期规划与编码智能。模型训练分为两个阶段：首先通过持续预训练提升模型知识与隐式编码能力，随后进行大规模强化学习，通过强化推理、精准的多步执行以及面向长期真实编码问题的连贯性改进端到端编码性能。我们开发了与部署模型一致的Cursor训练框架基础设施，配备同等工具与结构，并使用高度匹配真实问题的实验环境。为评估模型在日益复杂任务上的表现，我们引入了一个基于大型代码库（包含自身代码库）中真实软件工程问题的基准测试集。Composer 2 作为前沿级编码模型，展现了训练强领域专用模型的有效流程。在CursorBench评估中，模型相较前代Composer模型实现显著精度提升（61.3分）。在公开基准测试中，本模型在Terminal-Bench上取得61.7分，在SWE-bench多语言版本中取得73.7分，性能与当前最先进系统相当。