HCJun 19

JumpStarter: Human-AI Planning with Task-Structured Context Curation

Xuanming Zhang, Sitong Wang, Jenny Ma, Alyssa Hwang, Zhou Yu, Lydia B. Chilton
arXiv:2410.038829.94 citationsh-index: 8
Predicted impact top 23% in HC · last 90 daysOriginality Incremental advance
AI Analysis

For users of LLM-based planning assistants, this work addresses the bottleneck of manual context curation, offering a structured approach that yields higher-quality plans.

JumpStarter improves human-AI planning by dynamically decomposing goals into subtasks and scoping context to each decision point, outperforming ChatGPT in user study quality ratings and automatic simulations.

Human-AI collaboration on complex planning goals is bottlenecked by how LLM interfaces handle context: users must manually curate and re-surface relevant information across long and unstructured chat histories. Despite advances in long-context prompting and memory-augmented retrieval, this burden remains unresolved: users still have to identify and supply the right context at each decision point, regardless of how much the model can store or surface. We propose JumpStarter, a system that enables LLMs to collaborate with humans on complex goals by dynamically decomposing tasks to help users manage context. We specifically introduce task-structured context curation, a framework that breaks down a user's goal into a hierarchy of actionable subtasks and scopes context to localized decision points, enabling finer-grained personalization and reuse. The framework is realized through three core mechanisms: context elicitation, selection, and reuse. In a within-subjects user study, plans produced with JumpStarter were rated substantially higher in quality than those produced with ChatGPT. A complementary automatic simulation study shows that JumpStarter consistently outperforms ChatGPT baselines, planning and memory agents, and workflow ablations. These findings show that effective human-AI planning depends not on the volume of context provided, but on attaching the right context to the right subtask at the right time.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes