Martin Odersky
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
AI×1Prog. Lang.×1
Frequent co-authors
Research Timeline
2026
LACUNA: Safe Agents as Recursive Program Holes
The paper introduces LACUNA, a novel programming model that allows LLM agents to write code that shapes the runtime environment while maintaining strong type-checking safety guarantees.
Highlighted terms show continued research focus across papers
Papers
cs.AIcs.PLRecentMay 27, 2026
LACUNA: Safe Agents as Recursive Program Holes
Yaoyu Zhao, Yichen Xu, Oliver Bračevac, Cao Nguyen Pham +2 more
The paper introduces LACUNA, a novel programming model that allows LLM agents to write code that shapes the runtime environment while maintaining strong type-checking safety guarantees.
View →