{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T13:43:20Z","timestamp":1775569400457,"version":"3.50.1"},"reference-count":21,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data"],"abstract":"<jats:p>Agent-based systems built on large language models (LLMs) increasingly rely on complex internal reasoning processes, tool interactions, and memory mechanisms. However, the internal decision-making dynamics of such agents remain difficult to observe, analyze, and compare in a systematic manner. To address this limitation, we present AgentSec, a curated dataset of structured agent interaction traces designed to support the analysis of agent-level reasoning and action behaviors. The dataset consists of 30 deterministic and non-redundant scenario instances, each capturing a complete agent interaction session under a fixed and validated schema. Quantitatively, the 30 released sessions comprise 67 decision nodes and 45 tool calls (73.3% successful), with provenance graphs exhibiting an average depth of 4.53 (max 7) and a maximum branching factor of 3. Scenarios are organized according to a predefined taxonomy of agent behavioral patterns, including tool success and failure modes, fallback strategies, memory conflicts and overwrites, decision rollbacks, and provenance branching structures. Each scenario encodes a distinct analytical case rather than a parametric variation, enabling focused and interpretable study of agent decision-making processes. AgentSec provides detailed records of decision traces, tool calls, memory updates, and provenance relations, and is intended to facilitate reproducible research on agent behavior analysis, auditing, and evaluation. The dataset is released alongside its schema, scenario manifest, and validation tooling to support reuse and extension by the research community. Rather than serving as a large-scale performance benchmark, AgentSec is explicitly designed as a diagnostic and unit-test suite for auditing agent-level reasoning logic and provenance consistency under controlled structural conditions.<\/jats:p>","DOI":"10.3390\/data11040066","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T12:05:49Z","timestamp":1775563549000},"page":"66","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Dataset Capturing Decision Processes, Tool Interactions and Provenance Links in Autonomous AI Agents"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0276-6774","authenticated-orcid":false,"given":"Yasser","family":"Hmimou","sequence":"first","affiliation":[{"name":"Multidisciplinary Laboratory of Research and Innovation (LPRI), Moroccan School of Engineering Sciences (EMSI), Casablanca 20250, Morocco"},{"name":"Computing, Artificial Intelligence and Cyber Security Laboratory (2IACS), Higher Normal School of Technical Education (ENSET), Hassan II University of Casablanca, Casablanca 20360, Morocco"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3938-3566","authenticated-orcid":false,"given":"Mohamed","family":"Tabaa","sequence":"additional","affiliation":[{"name":"Multidisciplinary Laboratory of Research and Innovation (LPRI), Moroccan School of Engineering Sciences (EMSI), Casablanca 20250, Morocco"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7090-9098","authenticated-orcid":false,"given":"Azeddine","family":"Khiat","sequence":"additional","affiliation":[{"name":"Computing, Artificial Intelligence and Cyber Security Laboratory (2IACS), Higher Normal School of Technical Education (ENSET), Hassan II University of Casablanca, Casablanca 20360, Morocco"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1104-4896","authenticated-orcid":false,"given":"Zineb","family":"Hidila","sequence":"additional","affiliation":[{"name":"Multidisciplinary Laboratory of Research and Innovation (LPRI), Moroccan School of Engineering Sciences (EMSI), Casablanca 20250, Morocco"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"ref_1","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023, January 1\u20135). ReAct: Synergizing reasoning and acting in language models. Proceedings of the International Conference on Learning Representations (ICLR), Kigali, Rwanda."},{"key":"ref_2","unstructured":"Schick, T., Dwivedi-Yu, J., Dess\u00ec, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., and Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems (NeurIPS), Neural Information Processing Systems Foundation, Inc. (NeurIPS)."},{"key":"ref_3","unstructured":"Wang, G., Xie, Y., Jiang, Y., Mandlekar, A., Xiao, C., Zhu, Y., Fan, L., and Anandkumar, A. (2023). Voyager: An open-ended embodied agent with large language models. arXiv."},{"key":"ref_4","first-page":"8634","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume":"36","author":"Shinn","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"121101","DOI":"10.1007\/s11432-024-4222-0","article-title":"The rise and potential of large language model based agents: A survey","volume":"68","author":"Xi","year":"2023","journal-title":"Sci. China Inf. Sci."},{"key":"ref_6","unstructured":"Moreau, L., Missier, P., Belhajjame, K., B\u2019Far, R., Cheney, J., Coppens, S., Cresswell, S., Gil, Y., Groth, P., and Klyne, G. (2026, January 25). PROV-DM: The PROV Data Model. W3C Recommendation. Available online: https:\/\/www.w3.org\/TR\/prov-dm\/."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Moreau, L., and Groth, P. (2013). Provenance: An Introduction to PROV, Springer.","DOI":"10.1007\/978-3-031-79450-6"},{"key":"ref_8","unstructured":"Doshi-Velez, F., and Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett, P.N., and Inkpen, K. (2019). Guidelines for human-AI interaction. Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI 2019), Association for Computing Machinery (ACM).","DOI":"10.1145\/3290605.3300233"},{"key":"ref_10","unstructured":"Pearl, J., and Mackenzie, D. (2018). The Book of Why: The New Science of Cause and Effect, Basic Books."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"107980","DOI":"10.1016\/j.infsof.2025.107980","article-title":"Fair and square? Evaluating fairness of LLM-generated synthetic datasets","volume":"191","author":"Voria","year":"2025","journal-title":"Inf. Softw. Technol."},{"key":"ref_12","first-page":"28","article-title":"Blockchain-powered data provenance for AI model audits","volume":"1","author":"Jain","year":"2024","journal-title":"Sci. J. Artif. Intell. Blockchain Technol."},{"key":"ref_13","unstructured":"Mittal, S., Thakral, K., Singh, R., Vatsa, M., Glaser, T., Ferrer, C.F., and Hassner, T. (2023). On responsible machine learning datasets with fairness, privacy, and regulatory norms. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1038\/s42256-024-00878-8","article-title":"The data provenance initiative: A large-scale audit of dataset licensing and attribution in AI","volume":"6","author":"Longpre","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"ref_15","unstructured":"Lu, Y., Chen, L., Zhang, Y., Shen, M., Wang, H., Wang, X., van Rechem, C., Fu, T., and Wei, W. (2023). Machine learning for synthetic data generation: A review. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Bender, E.M., Gebru, T., McMillan-Major, A., and Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big?. Proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT), Association for Computing Machinery (ACM).","DOI":"10.1145\/3442188.3445922"},{"key":"ref_17","first-page":"46","article-title":"Trustworthy AI: From principles to practices","volume":"65","author":"Li","year":"2022","journal-title":"Commun. ACM"},{"key":"ref_18","unstructured":"Valmeekam, K., Olmo, A., Sreedharan, S., and Kambhampati, S. (2022). Large language models still can\u2019t plan: A benchmark for reasoning and planning. arXiv, Available online: https:\/\/arxiv.org\/abs\/2206.10498."},{"key":"ref_19","unstructured":"Creswell, A., and Shanahan, M. (2022). Faithful reasoning using large language models. arXiv."},{"key":"ref_20","unstructured":"Lyu, H., Sha, N., Qin, S., Yan, M., Xie, Y., and Wang, R. (2024, January 7\u201311). AgentBench: Evaluating LLMs as agents. Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Souza, R., Gueroudji, A., DeWitt, S., Rosendo, D., Ghosal, T., Ross, R., Balaprakash, P., and Ferreira da Silva, R. (2025). PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows. arXiv.","DOI":"10.1109\/eScience65000.2025.00093"}],"container-title":["Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5729\/11\/4\/66\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T12:43:22Z","timestamp":1775565802000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5729\/11\/4\/66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,25]]},"references-count":21,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["data11040066"],"URL":"https:\/\/doi.org\/10.3390\/data11040066","relation":{},"ISSN":["2306-5729"],"issn-type":[{"value":"2306-5729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,25]]}}}