AstaBench is a new benchmark suite for AI agents performing scientific research across domains, with evaluations of 57 agents showing that AI remains far from solving science research assistance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
AstaBench is a new benchmark suite for AI agents performing scientific research across domains, with evaluations of 57 agents showing that AI remains far from solving science research assistance.