近年来，机器人学习的发展让机器能够自主完成越来越多的任务。但在自主执行的背后，数据采集、失败诊断、训练方案调整和部署决策，仍然主要依赖研究者与工程师。机器人已经越来越会执行任务，但如何让它们持续改进，仍是一项由人主导的工作。自我改进智能体的研究为此提供了新的思路。系统可以根据反馈修改代码、积累经验或更新模型，并将有效的修改用于后续任务。不过，这些工作通常沿用预先设定的改进流程，模型和技能在更新，产生和筛选更新的方法却保持不变。而递归自我改进则进一步关注，这套改进流程能否也从经验中得到更新，使后续学习更加有效。
In recent years, robot learning advances have enabled machines to autonomously complete more tasks. But behind autonomous execution, data collection, failure diagnosis, training plan adjustment, and deployment decisions still mainly rely on researchers and engineers. Robots are increasingly good at executing tasks, but how to make them continuously improve remains a human-led endeavor. Self-improving agent research offers new ideas—systems can modify code, accumulate experience, or update models based on feedback, applying effective modifications to subsequent tasks. However, these works usually follow preset improvement procedures: models and skills update, but the methods producing and selecting updates remain unchanged. Recursive self-improvement further asks whether this improvement procedure can also update from experience, making subsequent learning more effective.
当递归自我改进进入物理世界，这一目标将面临更多困难。机器人获得的观测往往不完整且带有噪声，失败原因难以准确判断；验证一项修改需要反复试验，还伴随着环境复位、硬件损耗乃至不可逆后果。因此，数字环境中的自我改进方法若想适用于机器人，需要在物理反馈、试验成本和安全约束下进行重新审视。围绕这些问题，来自上海交通大学、加州大学伯克利分校、斯坦福大学、麻省理工大学、谷歌、微软、英伟达和小米等机构的研究者，在论文《Who Improves the Robot? Toward Physical Recursive Self-Improvement》将任务能力的更新与改进流程的更新纳入统一框架，梳理机器人如何利用物理经验持续改进，以及安全和验证机制如何支持这一过程。
When recursive self-improvement enters the physical world, this goal faces more difficulties. Robot observations are often incomplete and noisy; failure causes are hard to accurately determine; validating a modification requires repeated trials with environment resets, hardware wear, and even irreversible consequences. Therefore, self-improvement methods from digital environments must be re-examined under physical feedback, trial costs, and safety constraints. Around these issues, researchers from Shanghai Jiao Tong University, UC Berkeley, Stanford University, MIT, Google, Microsoft, NVIDIA, and Xiaomi, in the paper "Who Improves the Robot? Toward Physical Recursive Self-Improvement," integrate task capability updates and improvement process updates into a unified framework, reviewing how robots continuously improve using physical experience and how safety and validation mechanisms support this process.
论文围绕改进了什么、通过什么路径改进、怎样证明有效，给出了三个方面的贡献。首先，建立理解Physical RSI的统一框架。论文给出Physical RSI的定义与L0至L5分级，从更新的是任务能力还是改进流程，和收益局限于同一任务还是能够跨任务迁移两个维度，为比较不同研究提供共同的分析框架。其次，梳理从能力更新到改进流程演化的全链路实现路径。论文围绕Harness适应与模型训练，分析记忆、技能、工作流及训练方法如何影响任务执行和后续改进，并将安全控制与更新验证纳入同一分析。最后，明确检验递归增益所需的证据。在相同初始系统、经验和资源预算下，通过独立的跨任务评估，比较新旧改进流程产生的后续收益，并据此识别现有研究的证据缺口。
The paper offers three contributions around what was improved, through what path, and how to prove effectiveness. First, it establishes a unified framework for understanding Physical RSI, providing the definition and L0–L5 grading, using two dimensions—whether task capability or improvement procedure is updated, and whether gains are confined to the same task or transfer across tasks—to provide a common analytical framework for comparing different studies. Second, it reviews the full-chain implementation path from capability updates to improvement procedure evolution, analyzing how memory, skills, workflows, and training methods affect task execution and subsequent improvement around Harness adaptation and model training, incorporating safety control and update validation into the same analysis. Finally, it clarifies the evidence needed to test recursive gains—under the same initial system, experience, and resource budget, through independent cross-task evaluation, comparing subsequent gains produced by new versus old improvement procedures, identifying evidence gaps in existing research.
L0到L5的定级值得单独看。L0是没有自主产生并保留更新，只在每一次任务执行过程中重新规划，或改进依赖人工干预。L1是自主更新任务执行系统，在同一任务上获得收益，改进流程保持固定。L2是自主更新改进流程本身，在同一任务上获得收益。L3是自主更新任务执行系统，带来跨任务收益，改进流程保持固定。L4是自主更新改进流程本身，带来跨任务收益。L5是在L4基础上，通过独立、受控的比较，证实连续更新的新流程比上一版本带来更好的后续跨任务收益。这个分级的意义在于，它把机器人做得更好了和机器人改进自己的方法变得更有效了这两件事区分开了。前面讨论过贝塔无限的BetaMem做记忆策略的递归自我改进，也讨论过初光跃迁的Physical RSI、欧拉万象的Real-World RSI。这些工作大多停留在L1到L2，能更新任务执行系统或者改进流程本身，但还没有证实在相同条件下，新流程比旧流程带来更好的后续收益。
The L0–L5 grading deserves separate attention. L0 is no autonomous generation and retention of updates—only re-planning during each task execution, or improvement relying on human intervention. L1 is autonomously updating the task execution system, gaining on the same task while the improvement procedure stays fixed. L2 is autonomously updating the improvement procedure itself, gaining on the same task. L3 is autonomously updating the task execution system, bringing cross-task gains while the improvement procedure stays fixed. L4 is autonomously updating the improvement procedure itself, bringing cross-task gains. L5 is on top of L4, through independent, controlled comparison, proving continuously updated new procedures bring better subsequent cross-task gains than the previous version. This grading's significance is distinguishing "the robot got better" from "the robot's method of improving itself got more effective." Earlier we discussed Beta Infinite's BetaMem doing memory strategy recursive self-improvement, Chiuguang Yueqian's Physical RSI, and Ola Universe's Real-World RSI. These works mostly stay at L1 to L2—updating task execution systems or improvement procedures themselves, but not yet proving that under the same conditions, new procedures bring better subsequent gains than old ones.
论文梳理的实现路径分三块。Harness适应方面，模型外围的系统资源也能成为改进对象。执行反馈被用于诊断失败、更新记忆、技能和工作流。有效修改被保留，修改记录则支持后续诊断与方案选择。近期研究也开始进一步调整生成这些更新的方法，包括诊断指导、记忆构建策略和搜索程序，为将改进方法本身的演化引入物理场景提供了参考。模型训练方面，数据收集、模型更新和再次执行连接成训练闭环，持续将物理交互数据转化为后续改进。部分工作进一步将训练机制本身作为改进对象，数据准备方面，也已有研究根据学习效果调整数据配比、仿真分布或采样策略。
The paper's implementation path divides into three parts. On Harness adaptation, system resources outside the model can also become improvement objects. Execution feedback is used to diagnose failures, update memory, skills, and workflows. Effective modifications are retained; modification records support subsequent diagnosis and solution selection. Recent research also further adjusts the methods generating these updates, including diagnostic guidance, memory construction strategies, and search procedures, providing references for introducing improvement method evolution into physical scenarios. On model training, data collection, model updates, and re-execution connect into a training loop, continuously converting physical interaction data into subsequent improvements. Some works further treat the training mechanism itself as an improvement object; in data preparation, research has adjusted data ratios, simulation distributions, or sampling strategies based on learning effects.
安全方面，最终策略通过安全测试，不能说明此前的探索没有风险。安全强化学习已为探索过程提供约束，安全迁移研究则明确保障沿用的条件。这些进展主要针对特定组件和场景，如何在改进流程自身演化时维持安全保障，和评估学习过程中反复试验带来的风险，仍是Physical RSI面临的关键问题。验证方面，代码能运行只是第一关。修改是否修复了原先的失败，还要通过重新执行来判断；共享技能发生变化，也需要回测此前成功的任务。内部验证决定哪些更新被保留，外部独立评估器检验实际收益。如果验证器本身被修改，则需要由外部独立评估器判断新版本的效果，避免系统逐渐放宽自己的验收标准。
On safety, a final policy passing safety tests does not mean earlier exploration had no risk. Safe reinforcement learning has provided constraints for exploration; safe transfer research clarifies conditions for continued guarantees. These advances mainly target specific components and scenarios; how to maintain safety guarantees when the improvement procedure itself evolves, and assessing risks from repeated trials during learning, remain key Physical RSI issues. On validation, code running is only the first hurdle. Whether a modification fixed the original failure still needs re-execution to judge; when shared skills change, previously successful tasks also need regression testing. Internal validation decides which updates are retained; external independent evaluators test actual gains. If the validator itself is modified, external independent evaluators must judge the new version's effectiveness, preventing the system from gradually loosening its own acceptance criteria.
论文提出了六个仍待解决的问题。从不确定的物理经验中学习，如何提取可靠的学习信号，避免错误反馈随着改进机制的继承而不断放大。Harness组件间的因果归因，如何在有限的物理试验中找准修改对象，并分清每次修改的实际作用。改进闭环的非平稳性，在系统、环境和已有能力变化时，过去有效的修改和改进策略是否仍然有效。奖励投机与评估泄漏，如何防止系统利用漏洞获得高分，并保持评估的独立性。递归更新中的安全保持，如何在改进流程变化时维持安全保障并控制多轮试验的累积风险。递归增益的基准评测，后继系统表现更好，是因为数据更多、起点更强，还是改进机制更新带来的收益。
The paper proposes six unresolved questions. Learning from uncertain physical experience—how to extract reliable learning signals and avoid error feedback amplifying through inherited improvement mechanisms. Causal attribution among Harness components—how to pinpoint modification targets in limited physical trials and distinguish each modification's actual effect. Non-stationarity of the improvement loop—whether previously effective modifications and improvement strategies remain effective when systems, environments, and existing capabilities change. Reward hacking and evaluation leakage—how to prevent systems from exploiting loopholes for high scores and maintain evaluation independence. Safety preservation in recursive updates—how to maintain safety guarantees and control cumulative risks of multiple trials when improvement procedures change. Benchmark evaluation of recursive gains—whether successor systems perform better because of more data, stronger starting points, or gains from updated improvement mechanisms.
这篇论文和前面讨论的宇树H2-X、AGCO把Digit拉进收割机工厂、三菱电机把物理AI接进数控机床、亮源新创说泛化能力是规模化最大壁垒，是同一个产业阶段的不同侧面。那些讨论关注的是机器人能不能干活、能不能稳定干活、能不能规模化干活。这篇论文关注的是另一个问题，机器人在干活的过程中，能不能持续改进自己的干活方式，而且这种改进能不能被证明是有效的。前面讨论过硅谷和五道口的两种造神运动，也讨论过具身智能行业融资降温、IPO暂缓、收入合资格性受审视。在这个阶段，Physical RSI这个方向的价值不在于它能不能马上让机器人变得更强，而在于它提供了一个可以检验的框架，让越学越会学从一句口号，变成一个可以分级、可以评测、可以证伪的研究命题。
This paper, alongside the previously discussed Unitree H2-X, AGCO bringing Digit into a combine factory, Mitsubishi Electric connecting physical AI to CNC machines, and Liangyuan Xinsheng saying generalization is the biggest scaling barrier, are different sides of the same industry stage. Those discussions focused on whether robots can work, work stably, and work at scale. This paper focuses on another question—whether robots can continuously improve their way of working during work, and whether this improvement can be proven effective. Earlier we discussed Silicon Valley and Wudaokou's two "god-making" movements, embodied intelligence industry financing cooling, IPO postponements, and revenue eligibility scrutiny. At this stage, Physical RSI's value lies not in whether it can immediately make robots stronger but in providing a testable framework, turning "the more they learn, the better they learn" from a slogan into a research proposition that can be graded, evaluated, and falsified.
