外观
论文arXiv 2610.1122320 天前
SafeInferCom：通过验证器引导的生成中途干预实现机器人任务规划的安全推理时计算
原文链接：SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning（arXiv 2610.11223 · 发布日期：2026-10-08）
SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning
针对LRLM机器人任务规划中有效中间计划被覆盖和约束未解问题，SafeInferCom用验证器引导生成中途干预，并在多模型、多规划域、VirtualHome及真机演示中验证。
核心要点
- LRLM持续推理可能覆盖有效中间计划，或让约束违规悬而未决。
- 推理时监控器在不扰动原解码轨迹下，暴露并验证中间计划。
- SafeInferCom用形式化验证器保留有效计划，并引导生成中纠错。
- 相对一次推理提升成功率、加速纠错；结合迭代细化可减少token使用。
验证范围与局限：验证包括多个LRLM和规划域、VirtualHome评估，以及真实机械臂演示。
英文摘要 (Abstract)
Large Reasoning Language Models (LRLMs) enable multi-step reasoning for robotic task planning, but continued reasoning can overwrite valid intermediate plans or leave constraint violations unresolved, reducing planning reliability and wasting inference-time computation. We develop an inference-time monitor that exposes and verifies intermediate plans without disrupting the original decoding trajectory. Building on this monitor, we propose SafeInferCom, a formal verifier-guided framework that preserves valid intermediate plans and directs error correction during generation. Experiments across multiple LRLMs and planning domains reveal reasoning-response inconsistency and limited self-correction under one-shot inference. SafeInferCom improves planning success and accelerates error correction relative to one-shot inference. When combined with iterative refinement, it further improves success while reducing token usage compared with refinement alone. We additionally evaluate SafeInferCom in VirtualHome and provide a real-world robotic-arm demonstration.
作者：Weizhe Xu, Jialiang Fan, Mengyu Liu, Fanxin Kong
来源
本页事实对应的公开页面，以原文为准。