让大模型生成的机器人计划既合规又高质量，还保证可执行。
Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints
- 用元标记分解语法与语义约束，实现精准控制
- 将约束解码内存从107TB降至2GB，效率提升百万倍
- 真实机械臂实验中计划100%满足预条件和目标
大语言模型虽能生成流畅的机器人任务规划，但常违反必须满足的语法与语义约束。现有方法要么无法提供形式化保证（如基于亲和力评分或接地解码），要么牺牲常识能力（如符号规划器+大模型）。本文提出Meta-Ctrl，一种约束解码框架，在保证编码约束的前提下保留基础语言模型的规划质量。Meta-Ctrl引入‘元标记’——一组具身化的动作词汇，在词元层面强制语法，在动作层面确保前提条件、目标及顺序等语义约束，实现精确分解，使约束解码内存从超过107TB降至不足2GB。在LoTa-Bench协议下的WAH-NL数据集上，小型开源模型达到最高报告的子目标成功率，超越GPT-4表现，并在具身智能体接口上持续领先。进一步在真实桌面机器人上验证：所有生成计划均按构造满足预条件与目标。
原文摘要 · Abstract (English)
LLMs generate fluent plans for robots but routinely violate the syntactic and se8mantic constraints they must satisfy to execute, and existing remedies trade formal guarantees against plan quality: soft methods (affordance scoring, grounded decoding) give no guarantee, while symbolic planners (LLM+P) discard the LM's commonsense. We propose \textbf{Meta-Ctrl}, a constrained-decoding framework that guarantees the encoded constraints while preserving the base LM's plan quality. Meta-Ctrl introduces \emph{meta-tokens}---a compact vocabulary of grounded actions---enforcing syntax at the token level and semantics (preconditions, goals, ordering) at the action level, an exact factorization that cuts the memory of constrained decoding from over 107TB to under 2GB. With it, a small open-weight LM becomes competitive where it otherwise sits at the bottom of the leaderboard: on WAH-NL under the LoTa-Bench protocol it reaches the highest reported subgoal success rate, exceeding GPT-4's, with consistent gains across the Embodied Agent Interface. We further demonstrate it on a real tabletop robot, where every generated plan satisfies its preconditions and goals by construction. Project website: https://metactrlg.github.io
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。