17 Agentic AI & Robotics

How can goals become autonomous sequences of meaningful action?

Area 17: Agentic AI & Robotics

Master Question

How can goals become autonomous sequences of meaningful action?

What We Want to Discover

Turning a high level goal into a coherent sequence of concrete actions requires planning, tool use, monitoring, and the ability to revise a plan when reality departs from expectation. This area studies how agentic systems, including language model based agents connected to robotic actuators, should structure that process, and where the gap between symbolic planning and physical execution actually breaks.

Why It Matters

Interest in agentic systems is currently high, but many demonstrations remain brittle outside narrow, curated settings. Understanding what actually makes a goal directed sequence of actions robust is a precondition for taking these systems from demonstrations to dependable tools.

Core Concepts

  • Task decomposition and planning
  • Tool use and function calling
  • Plan monitoring and replanning
  • Grounding symbolic plans in physical action
  • Long horizon autonomy

Relevant Disciplines

  • Classical AI planning
  • Cognitive science of goal directed behaviour
  • Software engineering

Potential Mimicry Sources

  • Human project planning and replanning under obstacles
  • Hierarchical task execution in skilled professionals
  • Improvisation when a plan fails mid execution

Projects

No projects yet.

Active Questions

No projects yet, so there are no active derived questions to report.

Key Findings Across Projects

Pending. No projects in this area have produced findings yet.

Unresolved Questions

Pending.

Connections to Other Areas

Pending. Connections will be identified as projects in this area develop.