Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
From Prompt to Graph: Comparing LLM-Based Information Extraction Strategies in Domain-Specific Ontology Development
Xuan Liu, Ziyu Li, Mu He +10
Ontologies are essential for structuring domain knowledge, improving accessibility, sharing, and reuse. However, traditional ontology construction relies on manual annotation and c…
cs.AI2025
Rethinking Agent Design: From Top-Down Workflows to Bottom-Up Skill Evolution
Jiawei Du, Jinlong Wu, Yuzheng Chen +3
Most LLM-based agent frameworks adopt a top-down philosophy: humans decompose tasks, define workflows, and assign agents to execute each step. While effective on benchmark-style ta…