打破平均：通过诊断思维链与结构化引导克服机器人操作中的收敛默认行为
Breaking the Average: Overcoming Convergent Defaults in Robotic Manipulation via Diagnostic Chain-of-Thought and Structured Guidance
AI总结：
本研究针对VLA模型的收敛默认行为问题，提出含三阶段的无参数更新框架，在ManiSkill3仿真中验证其优于普通π₀.5与标准思维链提示。
摘要：
近期的视觉-语言-动作（VLA）模型，如π₀.5，通过在海量数据集上扩展行为克隆展现出出色的泛化能力。然而，这些模型常受分布收敛问题困扰，该现象指策略因训练数据中的模式平均而退化为“安全”但次优的平均行为，这往往会产生通用抓取策略——收敛默认行为，在受限或长尾场景中失效。本研究提出一种无需参数更新即可识别并修正此类行为的新型框架，引入三阶段方法：（1）默认行为探测，识别任务特定的模式坍塌；（2）诊断根本原因分析，利用VLA的潜在推理能力将次优动作背后的逻辑表述出来；（3）结构化引导注入，将具体、不同的替代方案编码为可复用的“Lens提示词”，以此改变采样分布。我们在ManiSkill3仿真环境中使用π₀.5验证该方法，假设其能通过有效打破复杂操作任务中的收敛默认行为，优于普通π₀.5与标准思维链提示。
英文摘要：
Recent Vision-Language-Action (VLA) models, such as $π_{0.5}$, have demonstrated impressive generalization capabilities by scaling behavior cloning across massive datasets. However, these models frequently suffer from distributional convergence, a phenomenon where the policy regresses to "safe" but suboptimal mean behaviors due to mode averaging in the training data. This often results in generic grasp strategies, Convergent Defaults, that fail in constrained or long-tail scenarios. In this work, we propose a novel framework to identify and correct these behaviors without parameter updates. We introduce a three-stage methodology: (1) Probing for Defaults, identifying task-specific mode collapse; (2) Diagnostic Root Cause Analysis, utilizing the VLA's latent reasoning capabilities to verbalize the logic behind suboptimal actions; and (3) Structured Guidance Injection, where concrete, distinct alternatives are encoded into reusable "Lens Prompts" that shift the sampling distribution. We validate this approach using $π_{0.5}$ in ManiSkill3 simulation environments. We hypothesize that our method outperforms vanilla $π_{0.5}$ and standard Chain-of-Thought prompting by effectively breaking convergent defaults in complex manipulation tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
