115 citations · 240 across the 29 of their papers we have counts for
33 papers
Memory as Middleware for Self-Improving AI Agents
K. R. Jayaram, Vatche Isahagian, Vinod Muthusamy +4
AI agents are stateless across sessions by default and therefore operationally amnesic: each session begins with little durable knowledge of prior failures, repairs, preferences, o…
Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents
Zidane Wright, Jason Tsay, Anupama Murthi +8
As AI agents move from demos into enterprise deployments, their failure modes become consequential: a misinterpreted tool argument can corrupt production data, a silent reasoning e…
Trajectory-Informed Memory Generation for Self-Improving Agent Systems
Gaodan Fang, Vatche Isahagian, K. R. Jayaram +4
LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they oft…
VOILA: Value-of-Information Guided Fidelity Selection for Cost-Aware Multimodal Question Answering
Rahul Atul Bhope, K. R. Jayaram, Vinod Muthusamy +3
Despite significant costs from retrieving and processing high-fidelity visual inputs, most multimodal vision-language systems operate at fixed fidelity levels. We introduce VOILA,…
Boosting Instruction Following at Scale
Ben Elder, Evelyn Duesterwald, Vinod Muthusamy
A typical approach developers follow to influence an LLM's behavior in an application is through careful manipulation of the prompt, such as by adding or modifying instructions. Ho…
FLOW-BENCH: Towards Conversational Generation of Enterprise Workflows
Evelyn Duesterwald, Siyu Huo, Vatche Isahagian +7
Business process automation (BPA) that leverages Large Language Models (LLMs) to convert natural language (NL) instructions into structured business process artifacts is becoming a…
OptiSeq: Ordering Examples On-The-Fly for In-Context Learning
Rahul Atul Bhope, Praveen Venkateswaran, K. R. Jayaram +3
Developers using LLMs and LLM-based agents in their applications have provided plenty of anecdotal evidence that in-context-learning (ICL) is fragile. In this paper, we show that i…
API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs
Kinjal Basu, Ibrahim Abdelaziz, Subhajit Chaudhury +7
There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks. As such, there…
A Case for Business Process-Specific Foundation Models
Yara Rizk, Praveen Venkateswaran, Vatche Isahagian +1
The inception of large language models has helped advance state-of-the-art performance on numerous natural language tasks. This has also opened the door for the development of foun…
FedGen: Generalizable Federated Learning for Sequential Data
Praveen Venkateswaran, Vatche Isahagian, Vinod Muthusamy +1
Existing federated learning models that follow the standard risk minimization paradigm of machine learning often fail to generalize in the presence of spurious correlations in the…
Hybrid Serverless Computing: Opportunities and Challenges
Paul Castro, Vatche Isahagian, Vinod Muthusamy +1
In recent years, there has been a surge in the adoption of serverless computing due to the ease of deployment, attractive pay-per-use pricing, and transparent horizontal auto-scali…
Just-in-Time Aggregation for Federated Learning
K. R. Jayaram, Ashish Verma, Gegi Thomas +1
The increasing number and scale of federated learning (FL) jobs necessitates resource efficient scheduling and management of aggregation to make the economics of cloud-hosted aggre…
A No-Code Low-Code Paradigm for Authoring Business Automations Using Natural Language
Michael Desmond, Evelyn Duesterwald, Vatche Isahagian +1
Most business process automation is still developed using traditional automation technologies such as workflow engines. These systems provide domain specific languages that require…
Natural Language Sentence Generation from API Specifications
Siyu Huo, Kushal Mukherjee, Jayachandu Bandlamudi +3
APIs are everywhere; they provide access to automation solutions that could help businesses automate some of their tasks. Unfortunately, they may not be accessible to the business…
Adaptive Aggregation For Federated Learning
K. R. Jayaram, Vinod Muthusamy, Gegi Thomas +2
Advances in federated learning (FL) algorithms,along with technologies like differential privacy and homomorphic encryption, have led to FL being increasingly adopted and used in m…
Extending LIME for Business Process Automation
Sohini Upadhyay, Vatche Isahagian, Vinod Muthusamy +1
AI business process applications automate high-stakes business decisions where there is an increasing demand to justify or explain the rationale behind algorithmic decisions. Busin…
Do's and Don'ts for Human and Digital Worker Integration
Vinod Muthusamy, Merve Unuvar, Hagen Völzer +1
Robotic process automation (RPA) and its next evolutionary stage, intelligent process automation, promise to drive improvements in efficiencies and process outcomes. However, how c…
From Robotic Process Automation to Intelligent Process Automation: Emerging Trends
Tathagata Chakraborti, Vatche Isahagian, Rania Khalaf +4
In this survey, we study how recent advances in machine intelligence are disrupting the world of business processes. Over the last decade, there has been steady progress towards th…
A Conversational Digital Assistant for Intelligent Process Automation
Yara Rizk, Vatche Isahagian, Scott Boag +4
Robotic process automation (RPA) has emerged as the leading approach to automate tasks in business processes. Moving away from back-end automation, RPA automated the mouse-click on…
PipeSim: Trace-driven Simulation of Large-Scale AI Operations Platforms
Thomas Rausch, Waldemar Hummer, Vinod Muthusamy
Operationalizing AI has become a major endeavor in both research and industry. Automated, operationalized pipelines that manage the AI application lifecycle will form a significant…
AI Trust in business processes: The need for process-aware explanations
Steve T. K. Jan, Vatche Ishakian, Vinod Muthusamy
Business processes underpin a large number of enterprise operations including processing loan applications, managing invoices, and insurance claims. There is a large opportunity fo…
FfDL : A Flexible Multi-tenant Deep Learning Platform
K. R. Jayaram, Vinod Muthusamy, Parijat Dube +9
Deep learning (DL) is becoming increasingly popular in several application domains and has made several new application features involving computer vision, speech recognition and s…
Towards Enterprise-Ready AI Deployments Minimizing the Risk of Consuming AI Models in Business Applications
Aleksander Slominski, Vinod Muthusamy, Vatche Ishakian
The stochastic nature of artificial intelligence (AI) models introduces risk to business applications that use AI models without careful consideration. This paper offers an approac…
BPM for the masses: empowering participants of Cognitive Business Processes
Aleksander Slominski, Vinod Muthusamy
Authoring, developing, monitoring, and analyzing business processes has requires both domain and IT expertise since Business Process Management tools and practices have focused on…