{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T09:46:57Z","timestamp":1769161617255,"version":"3.49.0"},"reference-count":68,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006192","name":"Advanced Scientific Computing Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006192","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,15]]},"DOI":"10.1109\/escience65000.2025.00086","type":"proceedings-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:34:49Z","timestamp":1759858489000},"page":"415-426","source":"Crossref","is-referenced-by-count":1,"title":["ControlA: Agentic Workflow Control Mechanisms for Reliable Science"],"prefix":"10.1109","author":[{"given":"Amal","family":"Gueroudji","sequence":"first","affiliation":[{"name":"Argonne National Laboratory,Mathematics and Computer Science Division,Lemont,IL,USA"}]},{"given":"Tanwi","family":"Mallick","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory,Mathematics and Computer Science Division,Lemont,IL,USA"}]},{"given":"Renan","family":"Souza","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory,National Center for Computational Sciences,Oak Ridge,TN,USA"}]},{"given":"Rafael Ferreira","family":"Da Silva","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory,National Center for Computational Sciences,Oak Ridge,TN,USA"}]},{"given":"Robert","family":"Ross","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory,Mathematics and Computer Science Division,Lemont,IL,USA"}]},{"given":"Matthieu","family":"Dorier","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory,Mathematics and Computer Science Division,Lemont,IL,USA"}]},{"given":"Philip","family":"Carns","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory,Mathematics and Computer Science Division,Lemont,IL,USA"}]},{"given":"Kyle","family":"Chard","sequence":"additional","affiliation":[{"name":"University of Chicago,Chicago,IL,USA"}]},{"given":"Ian","family":"Foster","sequence":"additional","affiliation":[{"name":"University of Chicago,Chicago,IL,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3702970"},{"key":"ref2","first-page":"126","article-title":"Fifth paradigm in science: A case study of an intelligence-driven material design","volume-title":"Engineering","volume":"24","author":"Leng","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3532853"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2025.3544940"},{"key":"ref6","article-title":"Agentic AI for scientific discovery: A survey of progress, challenges, and future directions","author":"Gridach","year":"2025"},{"key":"ref7","first-page":"2025","article-title":"SpatialAgent: An autonomous AI agent for spatial biology","author":"Wang","year":"2025","journal-title":"bioRxiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06792-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1149\/2.F09252IF"},{"key":"ref10","first-page":"2025","article-title":"Comparative evaluation of advanced AI reasoning models in pediatric clinical decision support: ChatGPT O1 vs. DeepSeek-R1","author":"Mondillo","year":"2025","journal-title":"medRxiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-90026-6_8"},{"key":"ref12","volume-title":"Multi-agent systems: an introduction to distributed artificial intelligence","volume":"1","author":"Ferber","year":"1999"},{"key":"ref13","article-title":"Agent to agent protocol","year":"2025"},{"key":"ref14","article-title":"Model context protocol","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref16","article-title":"Large language models and mathematical reasoning failures","author":"Boye","year":"2025"},{"key":"ref17","article-title":"The validation gap: A mechanistic analysis of how language models compute arithmetic but fail to validate it","author":"Bertolazzi","year":"2025"},{"key":"ref18","article-title":"Large language models struggle with unreasonability in math problems","author":"Ma","year":"2024"},{"key":"ref19","first-page":"69 022","article-title":"On the worst prompt performance of large language models","volume":"37","author":"Cao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.153"},{"key":"ref21","article-title":"Prompt-reverse inconsistency: LLM self-inconsistency beyond generative randomness and prompt paraphrasing","author":"Ahn","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-97910-1"},{"key":"ref23","article-title":"Agent Smith: A single image can jailbreak one million multimodal LLM agents exponentially fast","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Gu"},{"key":"ref24","article-title":"A Grassroots Network and Community Roadmap for Interconnected Autonomous Science Laboratories for Accelerated Discovery","volume-title":"1st Workshop on Workflows, Intelligent Scientific Data, and Optimization for Automated Management (WISDOM)","author":"Ferreira da Silva"},{"key":"ref25","volume-title":"Artificial intelligence: a modern approach","author":"Russell","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref27","article-title":"Efficient reasoning models: A survey","author":"Feng","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.240255"},{"key":"ref29","article-title":"New horizons in psychology","author":"Wason","year":"1966"},{"issue":"3","key":"ref30","first-page":"430","article-title":"Subjective probability: A judgment of representativeness","volume-title":"Cognitive Psychology","volume":"3","author":"Kahneman","year":"1972"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2218523120"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.741"},{"key":"ref33","article-title":"Standardization trends on safety and trustworthiness technology for advanced AI","author":"Jeon","year":"2024"},{"key":"ref34","article-title":"Safeguarding large language models: A survey","author":"Dong","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.210"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3664646.3664766"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.15007"},{"key":"ref39","first-page":"27 730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022"},{"key":"ref41","first-page":"129 696","article-title":"Many-shot jailbreaking","volume":"37","author":"Anil","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/app14167150"},{"key":"ref43","article-title":"Poisoned LangChain: Jailbreak LLMs by LangChain","author":"Wang","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.59287\/icaens.1127"},{"key":"ref45","volume-title":"Generative AI with LangChain: Build large language model (LLM) apps with Python, ChatGPT, and other LLMs","author":"Auffarth","year":"2023"},{"key":"ref46","article-title":"Autogen: Enabling next-gen LLM applications via multi-agent conversation","author":"Wu","year":"2023"},{"key":"ref47","article-title":"Agent AI with LangGraph: a modular framework for enhancing machine translation using large language models","author":"Wang","year":"2024"},{"key":"ref48","article-title":"Empowering scientific workflows with federated agents","author":"Pauloski","year":"2025"},{"key":"ref49","article-title":"DecodingTrust: A comprehensive assessment of trustworthiness in GPT models","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref50","article-title":"Agentbench: Evaluating LLMs as agents","author":"Liu","year":"2023"},{"key":"ref51","article-title":"Bells: A framework towards future proof benchmarks for the evaluation of LLM safeguards","author":"Dorn","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1998.703255"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3716550.3725155"},{"key":"ref54","article-title":"Llama Guard: LLM-based input-output safeguard for human-ai conversations","author":"Inan","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.92"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-industry.49"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714113"},{"key":"ref58","first-page":"54 932","article-title":"FVEL: interactive formal verification environment with large language models via theorem proving","volume":"37","author":"Lin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650138"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-W58399.2023.00065"},{"key":"ref61","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yao"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6544"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/e-Science62913.2024.10678731"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/eScience65000.2025.00093"},{"key":"ref65","article-title":"Evaluating evaluation metrics \u2013 the mirage of hallucination detection","author":"Kulkarni","year":"2025"},{"key":"ref66","article-title":"Chain of thought monitorability: A new and fragile opportunity for AI safety","author":"Korbak","year":"2025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/e-Science58273.2023.10254822"},{"key":"ref68","doi-asserted-by":"crossref","DOI":"10.3389\/fhpcp.2025.1638203","article-title":"Towards a persistent event streaming system for high-performance computing applications","author":"Dorier","year":"2025"}],"event":{"name":"2025 IEEE International Conference on eScience (eScience)","location":"Chicago, IL, USA","start":{"date-parts":[[2025,9,15]]},"end":{"date-parts":[[2025,9,18]]}},"container-title":["2025 IEEE International Conference on eScience (eScience)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11181463\/11181464\/11181468.pdf?arnumber=11181468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T04:51:57Z","timestamp":1759899117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11181468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/escience65000.2025.00086","relation":{},"subject":[],"published":{"date-parts":[[2025,9,15]]}}}