PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration

  • 类型:arxiv
  • 标识:2608.21031
  • 链接:https://arxiv.org/abs/2608.21031
  • 主分类:agent
  • 形态:method
  • 被引:1
  • 被引来源:Semantic Scholar
  • S2被引:1
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:PhysCaP augments code-as-policy frameworks with a physics-informed exploration layer that enables explicit information-seeking through interaction, and introduces training-free physical property extraction modules that estimate object mass and stiffness from robot proprioception without additional sensors.
  • OpenAlex ID:W7204118055
  • OpenAlex DOI:10.48550/arxiv.2608.21031
  • DOI:10.48550/arxiv.2608.21031
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/2608.21031
  • OpenAlex更新:2026-08-31
  • 待LLM分类:否
  • 标题中文:PhysCaP:用 physics-informed 探索对 Code-as-Policy Agent 进行 grounding
  • TLDR中文:PhysCaP 在 code-as-policy 框架上增加了物理信息驱动的探索层,使其能够通过交互进行显式的信息获取,并引入免训练的物理属性提取模块,仅凭机器人本体感知即可估计物体质量与刚度,无需额外传感器。
  • 来源文件:
  • /inbox/tom/_candidates/2026-08-25-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-25-agent-memory-tool-use-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]