preliminary desriptions and babble

paper/src/bib/references.bib

@@ -0,0 +1,62 @@
+@techReport{Imperva2025,
+   author = {Imperva},
+   title = {The Rapid Rise of Bots and the Unseen Risk for Business #2025BADBOTREPORT},
+   year = {2025}
+}
+
+@techReport{Xie,
+   abstract = {Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity. However, existing benchmarks either lack an interactive environment or are limited to environments specific to certain applications or domains, failing to reflect the diverse and complex nature of real-world computer use, thereby limiting the scope of tasks and agent scalability. To address this issue, we introduce OSWORLD, the first-of-its-kind scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across various operating systems such as Ubuntu, Windows, and macOS. OSWORLD can serve as a unified, integrated computer environment for assessing open-ended computer tasks that involve arbitrary applications. Building upon OSWORLD, we create a benchmark of 369 computer tasks involving real web and desktop apps in open domains, OS file I/O, and workflows spanning multiple applications. Each task example is derived from real-world computer use cases and includes a detailed initial state setup configuration and a custom execution-based evaluation script for reliable, reproducible evaluation. Extensive evaluation of state-of-the-art LLM/VLM-based agents on OSWORLD reveals significant deficiencies in their ability to serve as computer assistants. While humans can accomplish over 72.36% of the tasks, the best model achieves only 12.24% success, primarily struggling with GUI grounding and operational knowledge. Comprehensive analysis using OSWORLD provides valuable insights for developing multimodal generalist agents that were not possible with previous benchmarks. Our code, environment, baseline models, and data are publicly available at https://os-world.github.io.},
+   author = {Tianbao Xie and Danyang Zhang and Jixuan Chen and Xiaochuan Li and Siheng Zhao and Ruisheng Cao and Toh Jing Hua and Zhoujun Cheng and Dongchan Shin and Fangyu Lei and Yitao Liu and Yiheng Xu and Shuyan Zhou and Silvio Savarese and Caiming Xiong and Victor Zhong and Tao Yu},
+   title = {OSWORLD: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments},
+   url = {https://os-world.github.io}
+}
+
+@techReport{MarkNtelAdvisors2025,
+   author = {MarkNtel Advisors},
+   institution = {MarkNtel Advisors},
+   title = {Global AI Agent Market Research Report: Forecast (2026–2032)},
+   url = {https://www.marknteladvisors.com/research-library/ai-agent-market.html},
+   year = {2025}
+}
+
+@article{Xia2025,
+   abstract = {Large Language Models (LLMs) have enabled the emergence of LLM agents, systems capable of pursuing under-specified goals and adapting after deployment. Evaluating such agents is challenging because their behavior is open ended, probabilistic, and shaped by system-level interactions over time. Traditional evaluation methods, built around fixed benchmarks and static test suites, fail to capture emergent behaviors or support continuous adaptation across the lifecycle. To ground a more systematic approach, we conduct a multivocal literature review (MLR) synthesizing academic and industrial evaluation practices. The findings directly inform two empirically derived artifacts: a process model and a reference architecture that embed evaluation as a continuous, governing function rather than a terminal checkpoint. Together they constitute the evaluation-driven development and operations (EDDOps) approach, which unifies offline (development-time) and online (runtime) evaluation within a closed feedback loop. By making evaluation evidence drive both runtime adaptation and governed redevelopment, EDDOps supports safer, more traceable evolution of LLM agents aligned with changing objectives, user needs, and governance constraints.},
+   author = {Boming Xia and Qinghua Lu and Liming Zhu and Zhenchang Xing and Dehai Zhao and Hao Zhang},
+   month = {11},
+   title = {Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture},
+   url = {http://arxiv.org/abs/2411.13768},
+   year = {2025}
+}
+
+
+@misc{AmazonvsPerplexity,
+   author = {Shirin Ghaffary and Matt Day},
+   note = {Updated 2025-11-05},
+   title = {Amazon Sues to Stop Perplexity From Using AI Tool to Buy Stuff},
+   url = {https://www.bloomberg.com/news/articles/2025-11-04/amazon-demands-perplexity-stop-ai-agent-from-making-purchases}
+}
+
+
+@inproceedings{Mueller2019,
+   author = {Jonas W Mueller and Vasilis Syrgkanis and Matt Taddy},
+   booktitle = {Advances in Neural Information Processing Systems 32 (NeurIPS 2019)},
+   pages = {15442-15452},
+   title = {Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing},
+   url = {https://proceedings.neurips.cc/paper/2019/file/0a3df70393993583a13c0dd6686f3f32-Paper.pdf},
+   year = {2019}
+}
+
+@article{Amjad2017,
+   abstract = { In this paper, the question of interest is estimating true demand of a product at a given store location and time period in the retail environment based on a single noisy and potentially censored observation. To address this question, we introduce a %non-parametric framework to make inference from multiple time series. Somewhat surprisingly, we establish that the algorithm introduced for the purpose of "matrix completion" can be used to solve the relevant inference problem. Specifically, using the Universal Singular Value Thresholding (USVT) algorithm [7], we show that our estimator is consistent: the average mean squared error of the estimated average demand with respect to the true average demand goes to 0 as the number of store locations and time intervals increase to $\infty$. We establish naturally appealing properties of the resulting estimator both analytically as well as through a sequence of instructive simulations. Using a real dataset in retail (Walmart), we argue for the practical relevance of our approach. },
+   author = {Muhammad J. Amjad and Devavrat Shah},
+   doi = {10.1145/3154489},
+   issue = {2},
+   journal = {Proceedings of the ACM on Measurement and Analysis of Computing Systems},
+   month = {12},
+   pages = {1-28},
+   publisher = {Association for Computing Machinery (ACM)},
+   title = {Censored Demand Estimation in Retail},
+   volume = {1},
+   url = {https://par.nsf.gov/servlets/purl/10066022},
+   year = {2017}
+}