Composer 2 Technical Report
AI 摘要
Composer 2是一个专门为自主软件工程设计的模型，具有强大的长期规划和编码能力。
主要贡献
- 设计并训练了用于自主软件工程的Composer 2模型
- 开发了与部署模型相同的训练基础设施
- 提出了基于实际软件工程问题的评估基准CursorBench
方法论
采用两阶段训练方法：持续预训练提升知识和编码能力，大规模强化学习提升端到端编码性能。
原文摘要
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.