Abstract
Long-horizon web tasks often exhibit unstable behavior, where small decision errors propagate and lead to budget overruns or catastrophic failures. This study introduces a stability-oriented formulation of agentic reinforcement learning for web automation. Decision stability is quantified by the sensitivity of future cost and failure outcomes to small perturbations in current actions. The learning objective encourages policies that operate in low-sensitivity regions of the decision space while optimizing task success under multiple cost budgets. The proposed approach is evaluated on 1,000–2,000 web tasks with injected UI and latency perturbations. Results show that stability-oriented policies produce smoother trajectories, lower variance in cost consumption, and improved robustness to execution noise compared with standard constrained RL baselines.
References
Faroni, M., Umbrico, A., Beschi, M., Orlandini, A., Cesta, A., & Pedrocchi, N. (2023). Optimal task and motion planning and execution for multiagent systems in dynamic environments. IEEE Transactions on Cybernetics, 54(6), 3366-3377.
Gu, X., Yang, J., & Liu, M. (2025). Research on a Green Money Laundering Identification Framework and Risk Monitoring Mechanism Integrating Artificial Intelligence and Environmental Governance Data.
Miyai, A., Zhao, Z., Egashira, K., Sato, A., Sunada, T., Onohara, S., ... & Yamasaki, T. (2025). Webchorearena: Evaluating web browsing agents on realistic tedious web tasks. arXiv preprint arXiv:2506.01952.
Ma, Q., Yue, L., Xu, S., Shi, Y., & Liu, H. (2026). Web Agent Agentic Reinforcement Learning Decision Model Under Multi-Cost and Failure Risk Constraints.
Koh, J. Y., Lo, R., Jang, L., Duvvur, V., Lim, M., Huang, P. Y., ... & Fried, D. (2024, August). Visualwebarena: Evaluating multimodal agents on realistic visual web tasks. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 881-905).
Cai, B., Bai, W., Lu, Y., & Lu, K. (2024, June). Fuzz like a Pro: Using Auditor Knowledge to Detect Financial Vulnerabilities in Smart Contracts. In 2024 International Conference on Meta Computing (ICMC) (pp. 230-240). IEEE.
Alevizos, V., Gerolimos, N., Leligkou, E. A., Hompis, G., Priniotakis, G., & Papakostas, G. A. (2025). Sustainable Swarm Intelligence: Assessing Carbon-Aware Optimization in High-Performance AI Systems. Technologies, 13(10), 477.
Liu, S., Feng, H., & Liu, X. (2025). A Study on the Mechanism of Generative Design Tools' Impact on Visual Language Reconstruction: An Interactive Analysis of Semantic Mapping and User Cognition. Authorea Preprints.
Baduwal, M., & Paudel, P. (2026). Evaluating Agentic Artificial Intelligence: A Comprehensive Survey of Metrics, Benchmarks, and Methodologies. Authorea Preprints.
Du, Y. (2025). Research on Deep Learning Models for Forecasting Cross-Border Trade Demand Driven by Multi-Source Time-Series Data. Journal of Science, Innovation & Social Impact, 1(2), 63-70.
Ceusters, G., Camargo, L. R., Franke, R., Nowé, A., & Messagie, M. (2023). Safe reinforcement learning for multi-energy management systems with known constraint functions. Energy and AI, 12, 100227.
Patel, K. M. (2023). A practical reinforcement learning implementation approach for continuous process control. Computers & Chemical Engineering, 174, 108232.
Zhu, W., Yang, J., & Yao, Y. (2025, October). How Compliance Maturity Translates to Risk Reduction: A Multi-Case Comparison of Global Operations Using fsQCA and Hierarchical Bayesian Methods. In Proceedings of the 2025 2nd International Conference on Digital Economy and Computer Science (pp. 672-676).
Li, T., Xia, J., Liu, S., & Hong, E. (2025). Strategic Human Resource Leadership in Global Biopharmaceutical Enterprises: Integrating HR Analytics and Cross-Cultural.
Menon, A., Islam, A., Chatterjee, R., & Narang, V. (2025). A Cross-Layer Reliability and Resource Management Model for Ultra-Reliable Low-Latency Communication in Vehicular Ad Hoc Networks. Annual Review of Empirical Science, Quantitative Reasoning, and Systems Analysis, 15(10), 1-7.
Mao, Y., Ma, X., & Li, J. (2025). Research on API Security Gateway and Data Access Control Model for Multi-Tenant Full-Stack Systems.
Qiu, Y., & Wang, J. (2023, October). A machine learning approach to credit card customer segmentation for economic stability. In Proceedings of the 4th International Conference on Economic Management and Big Data Applications, ICEMBDA (pp. 27-29).
Sarros, C. A. (2022). Extending named data networking with delay-/disruption-tolerant and reputation-based trust mechanisms.
Zhu, W., Yao, Y., & Yang, J. (2025). Real-Time Risk Control Effects of Digital Compliance Dashboards: An Empirical Study Across Multiple Enterprises Using Process Mining, Anomaly Detection, and Interrupt Time Series.
Srivastava, K. K. (2025). S3: Stable Subgoal Selection by Constraining Uncertainty of Coarse Dynamics in Hierarchical Reinforcement Learning (Master's thesis, University of Massachusetts Lowell).
Mao, Y., Ma, X., & Li, J. (2025). Research on Web System Anomaly Detection and Intelligent Operations Based on Log Modeling and Self-Supervised Learning.
Flyvbjerg, B., Budzier, A., Christodoulou, M. D., & Zottoli, M. (2024). Uniqueness Bias: Why It Matters, How to Curb It. arXiv preprint arXiv:2408.07710.
Li, T., Xia, J., Liu, S., & Jiang, Y. (2025). Digital Transformation of Human Resources: From Consulting Frameworks to AI-Enabled Learning Management Systems.
Kumar, A. (2025). Disruptive Innovation in Indian Telecom Sector: A Case Study of Reliance Jio Infocomm Limited. Notion Press.
Gu, X., Liu, M., & Yang, J. (2025). Application and Effectiveness Evaluation of Federated Learning Methods in Anti-Money Laundering Collaborative Modeling Across Inter-Institutional Transaction Networks.

This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 Emily Chen, Liam O’Connor, Sarah Thompson (Author)