AutoMat benchmark shows current LLM coding agents achieve at most 54.1% success when reproducing computational materials science claims from papers.
CLAIMCHECK : How Grounded are LLM Critiques of Scientific Papers?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can Coding Agents Reproduce Findings in Computational Materials Science?
AutoMat benchmark shows current LLM coding agents achieve at most 54.1% success when reproducing computational materials science claims from papers.