Showing cs.SEShow all
2 papers · 1 filter
cs.SE2026
SIGIL: Skill Compilation for Reliable and Efficient Agent Execution
Jayanaka Dantanarayana, Savini Kashmira, Lingjia Tang +1
Agent skills describe reusable procedures, but runtime models must still interpret their instructions and coordinate execution. We introduce Skill Compilation, which translates the…
cs.SE2025
Prompt Less, Smile More: Semantic Engineering in Lieu of Prompt Engineering
Jayanaka L. Dantanarayana, Savini Kashmira, Xiaoyu Ma +5
AI-integrated applications increasingly rely on large language models (LLMs), but their intended behavior is not always fully specified by code. Meaning Typed Programming (MTP) aut…