外观
论文HF Daily Papers · arXiv 2610.360772 天前
The Trinity框架实现具身智能递归自改进，实测任务性能提升34点
本文由 AI 根据公开内容整理，可能有误，请以原文为准：The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents（HF Daily Papers · arXiv 2610.36077）
核心内容
针对多模态智能体规模化面临的环境构建昂贵及人工Harness迭代滞后瓶颈，研究提出The Trinity递归自改进框架。该框架耦合世界生成与Harness进化，将任务组织从表面类别重构为层级能力树。实验显示，进化后的Harness在28个训练基准上平均性能提升34点，在18个未见基准上提升26点，并在两个真实世界具身任务中完成验证，证明了跨模态能力迁移的有效性。
技术上引入Capability-Driven Real2Sim2Real机制：Creator将同节点异构任务的共性需求抽象为可验证仿真世界用于能力学习；Explorer沿能力树通过选择性继承进化可复用模块，形成固定拓扑下累积更新的Harness树；Evolver基于执行轨迹重组任务结构。此外，设计Capability-Aware Harness Router利用公共任务信息动态选择兼容模块配置，解决了传统方法难以应对任务多样性与复杂度增长的问题。
关键看点
- 递归自改进架构：耦合世界生成与Harness进化，通过Creator、Explorer、Evolver三角色将任务树重构为层级能力树，解决人工迭代滞后问题
- 能力驱动Sim2Real：抽象异构任务共性需求构建简化可验证仿真世界，支持能力学习与原任务迁移评估，降低异质环境构建成本
- 量化性能增益：进化Harness在28个训练基准均分提升34点，18个未见基准提升26点，并在真实具身任务中验证了泛化能力
- 动态路由机制：提出Capability-Aware Harness Router，基于公共任务信息从Harness树中选择兼容模块配置，实现能力复用与按需组合
工程与产业观察
该工作为具身智能数据飞轮提供了新范式，通过能力抽象与递归自改进解耦了对海量真实数据的依赖。其Real2Sim2Real与Harness树机制显著提升了算法在未见任务上的泛化效率，对降低机器人技能获取成本、加速长尾场景落地具有重要工程参考价值。
英文摘要 (Abstract)
Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness iteration cannot keep pace with growing task diversity and complexity. A key insight is that tasks with different modalities and surface forms can share the same underlying capability requirements. We therefore introduce The Trinity, a recursive self-improvement framework coupling world generation with Harness evolution through three roles: Creator, Explorer, and Evolver. Drawing on verified execution trajectories, Evolver shifts the basis of task organization from surface categories to shared requirements, reorganizing the original task tree into a hierarchical capability tree. We introduce Capability-Driven Real2Sim2Real: for heterogeneous tasks at the same node, Creator abstracts their common requirements into simplified, verifiable simulated worlds for capability learning, while evaluation on original tasks measures transfer. Along this capability tree, Explorer progressively evolves reusable capability modules through selective inheritance, forming a Harness tree whose validated updates accumulate across iterations within a fixed topology. The resulting Harnesses specialize in different capabilities, motivating a Capability-Aware Harness Router that uses public task information to select compatible module configurations from the tree. Our evolved Harnesses improve mean performance by 34 points across 28 training benchmarks and 26 points across 18 unseen benchmarks, including two real-world embodied tasks.
Hugging Face Daily Papers 热度：153 upvotes 作者：Weidong Tang, Ruiheng Wang, Jingxuan Zhang, Hexin Wang, Haoyuan Chen, Zhengfeiyang Zhang, Yixing Ma, Zichen Jiang, Ziyu Guo, Haodong Li, Zhengbo Jiao, Zhiqing Cui, Xinxiang Yin, Shuo Liang, Zhenglin W…
来源
本页事实对应的公开页面，以原文为准。