让大模型自动决定思考长度，又快又准还省资源。
ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code
- 用强化学习动态调节推理深度，避免无意义长思考
- 比传统方法少用70%以上token，性能相当
- 支持图文理解与代码推理，适合多模态任务
大型推理模型常出现‘过度思考’问题，在简单任务上生成冗长推理。现有缓解策略如长度惩罚或路由机制多为启发式且任务特定，缺乏通用框架。本文提出ARM2，通过增强长度感知的强化学习框架，统一实现多格式下的推理效率与性能自适应平衡。除自然语言推理外，ARM2还融合视觉理解，拓展至多模态场景；并引入可执行代码参与推理，相比传统思维链（CoT）显著降低令牌消耗，同时保持任务性能。实验表明，ARM2在性能上与采用GRPO训练的传统模型相当，平均令牌使用量减少超过70%。我们进一步开展广泛分析，验证了ARM2的有效性与设计合理性。
原文摘要 · Abstract (English)
Large Reasoning Models (LRMs) often suffer from the ``over-thinking'' problem, generating unnecessarily long reasoning on simple tasks. Some strategies have been proposed to mitigate this issue, such as length penalties or routing mechanisms, but they are typically heuristic and task-specific, lacking a general framework for adaptive reasoning. In this paper, we present ARM2, a unified model that adaptively balances reasoning performance and efficiency across multiple formats through a reinforcement learning framework augmented with length-aware optimization. Beyond conventional natural language inference, ARM2 integrates vision understanding, extending its applicability to multimodal. Moreover, ARM2 integrates executable code into reasoning, enabling substantial reductions in token cost while preserving task performance compared to long CoT. Experiments demonstrate that ARM2 achieves performance on par with traditional reasoning models trained with GRPO, while reducing token usage by over 70% on average. We further conduct extensive analyses to validate the effectiveness of ARM2 and the soundness of its design.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。