SciAgentArena is a new interactive benchmark for AI agents on scientific tasks that finds agents handle clear data-analysis workflows but struggle with novel insights, self-directed exploration, and open-ended questions.
AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
8 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
8
Pith papers citing it
1
external citations · Pith
abstract
AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging from general-purpose "deep research" systems to specialized science-specific agents, such as AI Scientist and AIGS. Rigorous evaluation of these agents is critical for progress. Yet existing benchmarks fall short on several fronts: they often (1) lack reproducible agent tools necessary for a controlled comparison of core agentic capabilities; (2) do not account for confounding variables such as model cost and tool access; (3) do not provide standardized interfaces for quick agent prototyping and evaluation; (4) fail to provide holistic, product-informed measures of real-world use cases such as science research; and (5) lack comprehensive baseline agents necessary to identify true advances. In response, we define principles and tooling for more rigorously benchmarking agents. Using these, we present AstaBench, a suite that provides a holistic measure of agentic ability to perform scientific research, comprising 2400+ problems spanning the entire scientific discovery process and multiple scientific domains, and including many problems inspired by actual user requests to deployed Asta agents. Our suite comes with the first scientific research environment with production-grade search tools that enable controlled, reproducible evaluation, better accounting for confounders. Alongside, we provide a comprehensive suite of nine science-optimized classes of Asta agents and numerous baselines. Our extensive evaluation of 57 agents across 22 agent classes reveals several interesting findings, most importantly that despite meaningful progress on certain individual aspects, AI remains far from solving the challenge of science research assistance.
citation-role summary
background 2
other 1
citation-polarity summary
years
2026 8representative citing papers
Herculean benchmark shows frontier agents handle trading and market insights better than hedging and auditing workflows that demand state consistency and structured verification.
MaD Physics is a new benchmark for evaluating AI agents on constrained information-seeking, model inference, and prediction in three physical environments with altered laws to avoid knowledge contamination.
Current AI agents fail to reliably invent transferable ML methods on a controlled 140-task benchmark, and more test-time compute or context does not remove the scientific-judgment bottleneck.
AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction reducing lower-wall Cf RMSE by 7.89% on the periodic hill at Reh=5600 while using a vision-language gate to detect 14 of 16 silent failures missed by solver checks.
LLM agents execute scientific tasks but fail to follow core scientific reasoning norms such as evidence consideration and belief revision based on refutations.
An empirical study evaluating tool-augmented LLM agents on 243 real-world energy analytics problems across data retrieval, knowledge interpretation, and quantitative modeling using domain-specific tools and multi-dimensional scoring.
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.
citing papers explorer
-
Benchmarking AI Agents for Addressing Scientific Challenges Across Scales
SciAgentArena is a new interactive benchmark for AI agents on scientific tasks that finds agents handle clear data-analysis workflows but struggle with novel insights, self-directed exploration, and open-ended questions.
-
Herculean: An Agentic Benchmark for Financial Intelligence
Herculean benchmark shows frontier agents handle trading and market insights better than hedging and auditing workflows that demand state consistency and structured verification.
-
MaD Physics: Evaluating information seeking under constraints in physical environments
MaD Physics is a new benchmark for evaluating AI agents on constrained information-seeking, model inference, and prediction in three physical environments with altered laws to avoid knowledge contamination.
-
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Current AI agents fail to reliably invent transferable ML methods on a controlled 140-task benchmark, and more test-time compute or context does not remove the scientific-judgment bottleneck.
-
AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction reducing lower-wall Cf RMSE by 7.89% on the periodic hill at Reh=5600 while using a vision-language gate to detect 14 of 16 silent failures missed by solver checks.
-
AI scientists produce results without reasoning scientifically
LLM agents execute scientific tasks but fail to follow core scientific reasoning norms such as evidence consideration and belief revision based on refutations.
-
How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?
An empirical study evaluating tool-augmented LLM agents on 243 real-world energy analytics problems across data retrieval, knowledge interpretation, and quantitative modeling using domain-specific tools and multi-dimensional scoring.
-
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.