Search papers, labs, and topics across Lattice.
This paper introduces SciAgentArena, a comprehensive benchmark designed to evaluate AI agents in real-world scientific research scenarios, addressing the limitations of existing benchmarks that fail to capture the complexity of scientific tasks. The study reveals that while current AI agents perform well in structured data-analysis workflows, they struggle with generating novel insights and addressing open-ended research questions. By identifying common failure modes and opportunities for improvement, this work lays the groundwork for enhancing the reliability and autonomy of AI agents in scientific contexts.
Current AI agents excel in structured tasks but falter at generating novel insights and tackling open-ended scientific challenges.
AI agents are increasingly being developed to accelerate scientific discovery, yet their practical capabilities in real research settings remain poorly understood. Existing benchmarks for AI agents rarely capture the complexity, heterogeneity, and extended reasoning required by scientific work, whereas benchmarks for scientific tasks often reduce research to static, direct problems and provide limited support for interactive evaluation. Here, we introduce SciAgentArena, a systematic benchmark for evaluating AI agents in real-world scientific research scenarios drawn from emerging needs across multiple domains. SciAgentArena comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents. Using this benchmark, we find that current agents can contribute effectively to well-specified data-analysis workflows, particularly when the task structure and evaluation criteria are clear. However, their performance remains uneven across scientific contexts: agents struggle to generate genuinely novel insights, sustain self-directed exploration, and formulate robust solutions for open-ended research questions. We further characterize common failure modes across agents and identify opportunities for improving their reliability, autonomy, and scientific reasoning. Together, SciAgentArena provides a practical framework for measuring progress in AI agents for science and for guiding the design of future agents capable of addressing complex scientific challenges. Full codes, tasks, and datasets can be accessed via this link: https://sciagentarena.github.io/.