Rules to Tools: Executable Checks for LLM Agents in Scientific Computing (Q7367483)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
No description defined
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Rules to Tools: Executable Checks for LLM Agents in Scientific Computing |
No description defined |
Statements
Rules to Tools: Executable Checks for LLM Agents in Scientific Computing (English)
0 references
29 September 2026
0 references
cs.AI
0 references
cs.SE
0 references
Jingjie Ning
0 references
Guojiang Zhao
0 references
Chen Xu
0 references
Shanshan Zhong
0 references
Xiaochuan Li
0 references
Ji Zeng
0 references
Guolin Ke
0 references
We provide an executable tool to check scientific computing requirements against written programs; across two task sets, our tool group achieves 26/30 complete repairs versus the text-only group's 29/30.
0 references
Rules to Tools
0 references
Executable Checks
0 references
Scientific Computing
0 references
Agent-Side Costs
0 references
Code Repair
0 references
