Subgoal Search For Complex Reasoning Tasks
Quick summary
arXiv:2108.11204v4 Announce Type: replace Abstract: Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) method. Its key component is a learned subgoal generator that produces a diversity of subgoals that are both achievable and closer to the solution. Using subgoals reduces the search space and induces a high-level search graph suitable for efficient planning. In this paper, we implement kSubS using a transformer-based subgoal module coupled with the classical best-first search fr
Key takeaways
- arXiv:2108.11204v4 Announce Type: replace Abstract: Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one.
- Inspired by this, we propose Subgoal Search (kSubS) method.
- Its key component is a learned subgoal generator that produces a diversity of subgoals that are both achievable and closer to the solution.
Why it matters
“Subgoal Search For Complex Reasoning Tasks” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments