AI 终于能「心里想、嘴上说」了
现在的 AI 助手，要么把每一步思考都写成文字，要么在内部黑箱里算完再给你答案。前者慢、费钱，后者你永远不知道它为什么这么答。这篇论文让 AI 在两种模式之间自由切换：简单问题直接心里过一遍，复杂任务才把关键步骤说出来给你看，而且切换的开关很轻，不拖慢速度。结果是：在数学、医学、搜索等 11 类任务上，准确率平均提升 10%，同时省掉一半以上的文字输出，推理速度快了近两倍，成本降了七成。它不是你明天就能用的产品，但它指向一个更聪明的方向——AI 不必事事向你解释，但该解释的时候，它知道。
📄 原文摘要(英文)
How can we build an agent that thinks beyond human language, yet still acts through it in the external environment? Modern LLM agents still reason and interact through text, while latent reasoning offers an efficient internal medium but lacks native tool access and reasoning transparency. We bridge these two directions with Hybrid Reasoning Agents (HybridAgents), which dynamically navigate between latent reasoning and text-based interaction throughout a unified generation process. Architecturally, a lightweight HybridLink enables seamless transitions between text and latent modes, while the agent's continuous working memory preserves lossless hybrid context across multiple turns. These designs preserve tool-integrated agentic capabilities while making latent thoughts directly inspectable. Building on this architecture, we further develop dedicated post-training algorithms for hybrid reasoning: HybridSFT stabilizes tool-integrated hybrid generation by teaching the backbone to coordinate with HybridLink, then HybridRL scales reasoning by learning when to think in latent space and when to act through text. We evaluate HybridAgent at 3 model scales across 11 benchmarks covering mathematics, science, medicine, search, and agentic reasoning. Compared with frontier LLM Agents and agentic frameworks spanning both text-based and latent methods, HybridAgent consistently improves performance by 10.4%, while delivering 35.5%-54.7% token reduction, 1.8x-2.6x faster inference, and 2.7x-3.7x cost savings. Code and data are available at https://github.com/togethercomputer/HybridAgent.