_version_ 1866912907459035136
author Lupidi, Alisia
Gauri, Bhavul
Foster, Thomas Simon
Omari, Bassel Al
Magka, Despoina
Pepe, Alberto
Audran-Reiss, Alexis
Aghamelu, Muna
Baldwin, Nicolas
Cipolina-Kun, Lucia
Gagnon-Audet, Jean-Christophe
Leow, Chee Hau
Lefdal, Sandra
Mossalam, Hossam
Moudgil, Abhinav
Nazir, Saba
Tewolde, Emanuel
Urrego, Isabel
Estape, Jordi Armengol
Budhiraja, Amar
Chaurasia, Gaurav
Charnalia, Abhishek
Dunfield, Derek
Hambardzumyan, Karen
Izcovich, Daniel
Josifoski, Martin
Mediratta, Ishita
Niu, Kelvin
Pathak, Parth
Shvartsman, Michael
Toledo, Edan
Protopopov, Anton
Raileanu, Roberta
Miller, Alexander
Shavrina, Tatiana
Foerster, Jakob
Bachrach, Yoram
author_facet Lupidi, Alisia
Gauri, Bhavul
Foster, Thomas Simon
Omari, Bassel Al
Magka, Despoina
Pepe, Alberto
Audran-Reiss, Alexis
Aghamelu, Muna
Baldwin, Nicolas
Cipolina-Kun, Lucia
Gagnon-Audet, Jean-Christophe
Leow, Chee Hau
Lefdal, Sandra
Mossalam, Hossam
Moudgil, Abhinav
Nazir, Saba
Tewolde, Emanuel
Urrego, Isabel
Estape, Jordi Armengol
Budhiraja, Amar
Chaurasia, Gaurav
Charnalia, Abhishek
Dunfield, Derek
Hambardzumyan, Karen
Izcovich, Daniel
Josifoski, Martin
Mediratta, Ishita
Niu, Kelvin
Pathak, Parth
Shvartsman, Michael
Toledo, Edan
Protopopov, Anton
Raileanu, Roberta
Miller, Alexander
Shavrina, Tatiana
Foerster, Jakob
Bachrach, Yoram
contents LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks sourced from state-of-the-art machine learning papers. These tasks span diverse domains, including language modeling, mathematics, bioinformatics, and time series forecasting. AIRS-Bench tasks assess agentic capabilities over the full research lifecycle -- including idea generation, experiment analysis and iterative refinement -- without providing baseline code. The AIRS-Bench task format is versatile, enabling easy integration of new tasks and rigorous comparison across different agentic frameworks. We establish baselines using frontier models paired with both sequential and parallel scaffolds. Our results show that agents exceed human SOTA in four tasks but fail to match it in sixteen others. Even when agents surpass human benchmarks, they do not reach the theoretical performance ceiling for the underlying tasks. These findings indicate that AIRS-Bench is far from saturated and offers substantial room for improvement. We open-source the AIRS-Bench task definitions and evaluation code to catalyze further development in autonomous scientific research.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06855
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents
Lupidi, Alisia
Gauri, Bhavul
Foster, Thomas Simon
Omari, Bassel Al
Magka, Despoina
Pepe, Alberto
Audran-Reiss, Alexis
Aghamelu, Muna
Baldwin, Nicolas
Cipolina-Kun, Lucia
Gagnon-Audet, Jean-Christophe
Leow, Chee Hau
Lefdal, Sandra
Mossalam, Hossam
Moudgil, Abhinav
Nazir, Saba
Tewolde, Emanuel
Urrego, Isabel
Estape, Jordi Armengol
Budhiraja, Amar
Chaurasia, Gaurav
Charnalia, Abhishek
Dunfield, Derek
Hambardzumyan, Karen
Izcovich, Daniel
Josifoski, Martin
Mediratta, Ishita
Niu, Kelvin
Pathak, Parth
Shvartsman, Michael
Toledo, Edan
Protopopov, Anton
Raileanu, Roberta
Miller, Alexander
Shavrina, Tatiana
Foerster, Jakob
Bachrach, Yoram
Artificial Intelligence
LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks sourced from state-of-the-art machine learning papers. These tasks span diverse domains, including language modeling, mathematics, bioinformatics, and time series forecasting. AIRS-Bench tasks assess agentic capabilities over the full research lifecycle -- including idea generation, experiment analysis and iterative refinement -- without providing baseline code. The AIRS-Bench task format is versatile, enabling easy integration of new tasks and rigorous comparison across different agentic frameworks. We establish baselines using frontier models paired with both sequential and parallel scaffolds. Our results show that agents exceed human SOTA in four tasks but fail to match it in sixteen others. Even when agents surpass human benchmarks, they do not reach the theoretical performance ceiling for the underlying tasks. These findings indicate that AIRS-Bench is far from saturated and offers substantial room for improvement. We open-source the AIRS-Bench task definitions and evaluation code to catalyze further development in autonomous scientific research.
title AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2602.06855