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业化模型。该模型展现出强大的长期规划能力与编程智能，同时保持高效解决交互式问题的能力。模型训练分为两个阶段：首先通过持续预训练提升模型的知识储备与潜在编码能力，随后通过大规模强化学习增强端到端编码性能——具体通过强化推理能力、精确的多步骤执行以及长周期真实编码问题的连贯性来实现。我们开发了与部署模型相同的Cursor训练框架基础设施，配备等效工具与结构，并使用紧密贴合真实问题的环境。为衡量模型在处理日益复杂任务时的性能，我们引入了一个基于大规模代码库（包括自有代码库）中真实软件工程问题的基准测试。Composer 2 作为前沿级编码模型，展示了训练强领域专业化模型的可行流程。在CursorBench评估中，该模型相比前代Composer模型实现了显著精度提升（61.3）。在公开基准测试中，模型在Terminal-Bench和SWE-bench Multilingual（基于自有框架）上分别获得61.7分和73.7分，性能与当前最先进系统相当。