Results for "sub-goals"

Decomposing goals into sub-tasks.

Breaking tasks into sub-steps.

Goals useful regardless of final objective.

Ensuring model behavior matches human goals, norms, and constraints, including reducing harmful or deceptive outputs.

A dataset + metric suite for comparing models; can be gamed or misaligned with real-world goals.

Attacks that manipulate model instructions (especially via retrieved content) to override system goals or exfiltrate data.

A system that perceives state, selects actions, and pursues goals—often combining LLM reasoning with tools and memory.

Methods for breaking goals into steps; can be classical (A*, STRIPS) or LLM-driven with tool calls.

System that independently pursues goals over time.

Ensuring AI systems pursue intended human goals.

Correctly specifying goals.

Inferring human goals from behavior.

Intelligence and goals are independent.