PHREEQC-MCQ-200 benchmark shows simulator access raises aggregate accuracy for tool-augmented agents on aqueous geochemistry tasks but produces non-monotonic gains and output-protocol sensitivity.
Nature Chemistry , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PHREEQC-MCQ-200: A Diagnostic Benchmark for Tool-Augmented Scientific Simulator Agents
PHREEQC-MCQ-200 benchmark shows simulator access raises aggregate accuracy for tool-augmented agents on aqueous geochemistry tasks but produces non-monotonic gains and output-protocol sensitivity.