# Composer 2 Technical Report

arXiv: https://arxiv.org/abs/2603.24477 · HTML: https://mlsanity.com/paper/2603.24477/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 62 of its 83 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 62)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)

## Built on by (most cited first, 22 of 22)

- [SWE-chat: Coding Agent Interactions From Real Users in the Wild](https://mlsanity.com/paper/2604.20779/) (2026)
- [Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents](https://mlsanity.com/paper/2604.15877/) (2026)
- [Agent-as-a-Router: Agentic Model Routing for Coding Tasks](https://mlsanity.com/paper/2606.22902/) (2026)
- [CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks](https://mlsanity.com/paper/2608.06352/) (2026)
- [Poly-EPO: Training Exploratory Reasoning Models](https://mlsanity.com/paper/2604.17654/) (2026)
- [GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning](https://mlsanity.com/paper/2604.02721/) (2026)
- [Guardrails Beat Guidance: A Large-Scale Study of Rules, Skills, and Persistent Configuration for Coding Agents](https://mlsanity.com/paper/2604.11088/) (2026)
- [Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams](https://mlsanity.com/paper/2606.20629/) (2026)
- [(Im)Paired Programming: Coding Agents Improve Productivity but Harm Understanding](https://mlsanity.com/paper/2607.26375/) (2026)
- [Prefix Sliding for efficient test-time scaling](https://mlsanity.com/paper/2608.26070/) (2026)
- [Towards a Risk Assessment of Malicious Skill Files in Coding Agents](https://mlsanity.com/paper/2608.05223/) (2026)
- [Context Language Models](https://mlsanity.com/paper/2609.37725/) (2026)
- [Reward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models](https://mlsanity.com/paper/2604.15577/) (2026)
- [Beyond Distribution Sharpening: The Importance of Task Rewards](https://mlsanity.com/paper/2604.16259/) (2026)
- [Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents](https://mlsanity.com/paper/2606.21732/) (2026)
- [Detecting AI Coding Agents in Open Source: A Validated Multi-Method Census of 180 Million Repositories](https://mlsanity.com/paper/2606.24429/) (2026)
- [AgentOmnia: Scaling Agentic Models for Full-Scenario Applications](https://mlsanity.com/paper/2607.23124/) (2026)
- [Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings](https://mlsanity.com/paper/2609.03177/) (2026)
- [Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching](https://mlsanity.com/paper/2609.07303/) (2026)
- [Mixture-of-Kittens: MoE Megakernel for NVL72s](https://mlsanity.com/paper/2609.36070/) (2026)
- [TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning](https://mlsanity.com/paper/2610.07043/) (2026)
- [NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale](https://mlsanity.com/paper/2610.08430/) (2026)

## Abstract (arXiv)

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.