arXiv subjects

Vatche Isahagian

Publications and source records attributed to Vatche Isahagian.

At least 19 recordsLinked to original sources

arXiv2026

Trajectory-Informed Memory Generation for Self-Improving Agent Systems

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar errors, and miss opportunities to apply successful strategies from past executions. We present a novel framework for automatically extracting actionable learnings from agent execution trajectories and utilizing them to improve future performance through contextual memory retrieval. Our approach comprises four components: (1) a Trajectory Intelligence Extractor that performs semantic analysis of agent reasoning patterns, (2) a Decision Attribution Analyzer that identifies which decisions and reasoning steps led to failures, recoveries, or inefficiencies, (3) a Contextual Learning Generator that produces three types of guidance -- strategy tips from successful patterns, recovery tips from failure handling, and optimization tips from inefficient but successful executions, and (4) an Adaptive Memory Retrieval System that injects relevant learnings into agent prompts based on multi-dimensional similarity. Unlike existing memory systems that store generic conversational facts, our framework understands execution patterns, extracts structured learnings with provenance, and retrieves guidance tailored to specific task contexts. Evaluation on the AppWorld benchmark demonstrates consistent improvements, with up to 14.3 percentage point gains in scenario goal completion on held-out tasks and particularly strong benefits on complex tasks (28.5~pp scenario goal improvement, a 149\% relative increase).

cs.AI↗

arXiv2026

VOILA: Value-of-Information Guided Fidelity Selection for Cost-Aware Multimodal Question Answering

Despite significant costs from retrieving and processing high-fidelity visual inputs, most multimodal vision-language systems operate at fixed fidelity levels. We introduce VOILA, a framework for Value-Of-Information-driven adaptive fidelity selection in Visual Question Answering (VQA) that optimizes what information to retrieve before model execution. Given a query, VOILA uses a two-stage pipeline: a gradient-boosted regressor estimates correctness likelihood at each fidelity from question features alone, then an isotonic calibrator refines these probabilities for reliable decision-making. The system selects the minimum-cost fidelity maximizing expected utility given predicted accuracy and retrieval costs. We evaluate VOILA across three deployment scenarios using five datasets (VQA-v2, GQA, TextVQA, LoCoMo, FloodNet) and six Vision-Language Models (VLMs) with 7B-235B parameters. VOILA consistently achieves 50-60% cost reductions while retaining 90-95% of full-resolution accuracy across diverse query types and model architectures, demonstrating that pre-retrieval fidelity selection is vital to optimize multimodal inference under resource constraints.

cs.CV↗

arXiv2025

On Automating Security Policies with Contemporary LLMs

The complexity of modern computing environments and the growing sophistication of cyber threats necessitate a more robust, adaptive, and automated approach to security enforcement. In this paper, we present a framework leveraging large language models (LLMs) for automating attack mitigation policy compliance through an innovative combination of in-context learning and retrieval-augmented generation (RAG). We begin by describing how our system collects and manages both tool and API specifications, storing them in a vector database to enable efficient retrieval of relevant information. We then detail the architectural pipeline that first decomposes high-level mitigation policies into discrete tasks and subsequently translates each task into a set of actionable API calls. Our empirical evaluation, conducted using publicly available CTI policies in STIXv2 format and Windows API documentation, demonstrates significant improvements in precision, recall, and F1-score when employing RAG compared to a non-RAG baseline.

cs.CR↗

arXiv2025

FLOW-BENCH: Towards Conversational Generation of Enterprise Workflows

Business process automation (BPA) that leverages Large Language Models (LLMs) to convert natural language (NL) instructions into structured business process artifacts is becoming a hot research topic. This paper makes two technical contributions -- (i) FLOW-BENCH, a high quality dataset of paired natural language instructions and structured business process definitions to evaluate NL-based BPA tools, and support bourgeoning research in this area, and (ii) FLOW-GEN, our approach to utilize LLMs to translate natural language into an intermediate representation with Python syntax that facilitates final conversion into widely adopted business process definition languages, such as BPMN and DMN. We bootstrap FLOW-BENCH by demonstrating how it can be used to evaluate the components of FLOW-GEN across eight LLMs of varying sizes. We hope that FLOW-GEN and FLOW-BENCH catalyze further research in BPA making it more accessible to novice and expert users.

cs.AI↗

arXiv2025

OptiSeq: Ordering Examples On-The-Fly for In-Context Learning

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 in addition to the quantity and quality of examples, the order in which the in-context examples are listed in the prompt affects the output of the LLM and, consequently, their performance. While prior work has explored improving ICL through dataset-dependent techniques, we introduce OptiSeq, a purely inference-time, dataset-free optimization method that efficiently determines the best example order. OptiSeq leverages log probabilities of LLM-generated outputs to systematically prune the search space of possible orderings and recommend the best order(s) by distinguishing orderings that yield high levels of accuracy and those that underperform. Extensive empirical evaluation on multiple LLMs, datasets, and prompts demonstrate that OptiSeq improves accuracy by 5.5 - 10.5 percentage points across multiple tasks.

cs.LG↗

arXiv2023

TaskDiff: A Similarity Metric for Task-Oriented Conversations

The popularity of conversational digital assistants has resulted in the availability of large amounts of conversational data which can be utilized for improved user experience and personalized response generation. Building these assistants using popular large language models like ChatGPT also require additional emphasis on prompt engineering and evaluation methods. Textual similarity metrics are a key ingredient for such analysis and evaluations. While many similarity metrics have been proposed in the literature, they have not proven effective for task-oriented conversations as they do not take advantage of unique conversational features. To address this gap, we present TaskDiff, a novel conversational similarity metric that utilizes different dialogue components (utterances, intents, and slots) and their distributions to compute similarity. Extensive experimental evaluation of TaskDiff on a benchmark dataset demonstrates its superior performance and improved robustness over other related approaches.

cs.CL↗

arXiv2023

DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning

Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue. Existing approaches use hand-crafted templates and additional slot information to fine-tune and prompt large pre-trained language models and elicit slot values from the dialogue context. Significant manual effort and domain knowledge is required to design effective prompts, limiting the generalizability of these approaches to new domains and tasks. In this work, we propose DiSTRICT, a generalizable in-context tuning approach for DST that retrieves highly relevant training examples for a given dialogue to fine-tune the model without any hand-crafted templates. Experiments with the MultiWOZ benchmark datasets show that DiSTRICT outperforms existing approaches in various zero-shot and few-shot settings using a much smaller model, thereby providing an important advantage for real-world deployments that often have limited resource availability.

cs.CL↗

arXiv2023

ProtoNER: Few shot Incremental Learning for Named Entity Recognition using Prototypical Networks

Key value pair (KVP) extraction or Named Entity Recognition(NER) from visually rich documents has been an active area of research in document understanding and data extraction domain. Several transformer based models such as LayoutLMv2, LayoutLMv3, and LiLT have emerged achieving state of the art results. However, addition of even a single new class to the existing model requires (a) re-annotation of entire training dataset to include this new class and (b) retraining the model again. Both of these issues really slow down the deployment of updated model. \\ We present \textbf{ProtoNER}: Prototypical Network based end-to-end KVP extraction model that allows addition of new classes to an existing model while requiring minimal number of newly annotated training samples. The key contributions of our model are: (1) No dependency on dataset used for initial training of the model, which alleviates the need to retain original training dataset for longer duration as well as data re-annotation which is very time consuming task, (2) No intermediate synthetic data generation which tends to add noise and results in model's performance degradation, and (3) Hybrid loss function which allows model to retain knowledge about older classes as well as learn about newly added classes.\\ Experimental results show that ProtoNER finetuned with just 30 samples is able to achieve similar results for the newly added classes as that of regular model finetuned with 2600 samples.

cs.CL↗

arXiv2023

FedGen: Generalizable Federated Learning for Sequential Data

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 training data. In many real-world distributed settings, spurious correlations exist due to biases and data sampling issues on distributed devices or clients that can erroneously influence models. Current generalization approaches are designed for centralized training and attempt to identify features that have an invariant causal relationship with the target, thereby reducing the effect of spurious features. However, such invariant risk minimization approaches rely on apriori knowledge of training data distributions which is hard to obtain in many applications. In this work, we present a generalizable federated learning framework called FedGen, which allows clients to identify and distinguish between spurious and invariant features in a collaborative manner without prior knowledge of training distributions. We evaluate our approach on real-world datasets from different domains and show that FedGen results in models that achieve significantly better generalization and can outperform the accuracy of current federated learning approaches by over 24%.

cs.LG↗

arXiv2022

A Case for Business Process-Specific Foundation Models

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 foundation models for other domains and data modalities such as images, code, and music. In this paper, we argue that business process data representations have unique characteristics that warrant the development of a new class of foundation models to handle tasks like process mining, optimization, and decision making. These models should also tackle the unique challenges of applying AI to business processes which include data scarcity, multi-modal representations, domain specific terminology, and privacy concerns.

cs.AI↗

arXiv2022

Hybrid Serverless Computing: Opportunities and Challenges

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-scaling. At the same time, infrastructure advancements such as the emergence of 5G networks and the explosion of devices connected to Internet known as Internet of Things (IoT), as well as new application requirements that constrain where computation and data can happen, will expand the reach of Cloud computing beyond traditional data centers into Hybrid Cloud. Digital transformation due to the pandemic, which accelerated changes to the workforce and spurred further adoption of AI, is expected to accelerate and the emergent Hybrid Cloud market could potentially expand to over trillion dollars. In the Hybrid Cloud environment, driven by the serverless tenants there will be an increased need to focus on enabling productive work for application builders that are using a distributed platform including public clouds, private clouds, and edge systems. In this chapter we investigate how far serverless computing can be extended to become Hybrid Serverless Computing.

cs.DC↗

arXiv2022

A No-Code Low-Code Paradigm for Authoring Business Automations Using Natural Language

Most business process automation is still developed using traditional automation technologies such as workflow engines. These systems provide domain specific languages that require both business knowledge and programming skills to effectively use. As such, business users often lack adequate programming skills to fully leverage these code oriented environments. We propose a paradigm for the construction of business automations using natural language. The approach applies a large language model to translate business rules and automations described in natural language, into a domain specific language interpretable by a business rule engine. We compare the performance of various language model configurations, across various target domains, and explore the use of constrained decoding to ensure syntactically correct generation of output.

cs.CL↗

arXiv2022

Natural Language Sentence Generation from API Specifications

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 users who need them but are not equipped with the necessary technical skills to leverage them. Wrapping these APIs with chatbot capabilities is one solution to make these automation solutions interactive. In this work, we propose a system to generate sentences to train intent recognition models, a crucial component within chatbots to understand natural language utterances from users. Evaluation of our approach based on deep learning models showed promising and inspiring results, and the human-in-the-loop interaction will provide further improvement on the system.

cs.CL↗

arXiv2021

Extending LIME for Business Process Automation

AI business process applications automate high-stakes business decisions where there is an increasing demand to justify or explain the rationale behind algorithmic decisions. Business process applications have ordering or constraints on tasks and feature values that cause lightweight, model-agnostic, existing explanation methods like LIME to fail. In response, we propose a local explanation framework extending LIME for explaining AI business process applications. Empirical evaluation of our extension underscores the advantage of our approach in the business process setting.

cs.AI↗

arXiv2021

LIBRA: An Economical Hybrid Approach for Cloud Applications with Strict SLAs

Function-as-a-Service (FaaS) has recently emerged to reduce the deployment cost of running cloud applications compared to Infrastructure-as-a-Service (IaaS). FaaS follows a serverless 'pay-as-you-go' computing model; it comes at a higher cost per unit of execution time but typically application functions experience lower provisioning time (startup delay). IaaS requires the provisioning of Virtual Machines, which typically suffer from longer cold-start delays that cause higher queuing delays and higher request drop rates. We present LIBRA, a balanced (hybrid) approach that leverages both VM-based and serverless resources to efficiently manage cloud resources for the applications. LIBRA closely monitors the application demand and provisions appropriate VM and serverless resources such that the running cost is minimized and Service-Level Agreements are met. Unlike state of the art, LIBRA not only hides VM cold-start delays, and hence reduces response time, by leveraging serverless, but also directs a low-rate bursty portion of the demand to serverless where it would be less costly than spinning up new VMs. We evaluate LIBRA on real traces in a simulated environment as well as on the AWS commercial cloud. Our results show that LIBRA outperforms other resource-provisioning policies, including a recent hybrid approach - LIBRA achieves more than 85% reduction in SLA violations and up to 53% cost savings.

cs.DC↗

arXiv2020

A Conversational Digital Assistant for Intelligent Process Automation

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 user interfaces; this outside-in approach reduced the overhead of updating legacy software. However, its many shortcomings, namely its lack of accessibility to business users, have prevented its widespread adoption in highly regulated industries. In this work, we explore interactive automation in the form of a conversational digital assistant. It allows business users to interact with and customize their automation solutions through natural language. The framework, which creates such assistants, relies on a multi-agent orchestration model and conversational wrappers for autonomous agents including RPAs. We demonstrate the effectiveness of our proposed approach on a loan approval business process and a travel preapproval business process.

cs.AI↗

arXiv2020

From Robotic Process Automation to Intelligent Process Automation: Emerging Trends

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 the automation of business processes under the umbrella of ``robotic process automation'' (RPA). However, we are currently at an inflection point in this evolution, as a new paradigm called ``Intelligent Process Automation'' (IPA) emerges, bringing machine learning (ML) and artificial intelligence (AI) technologies to bear in order to improve business process outcomes. The purpose of this paper is to provide a survey of this emerging theme and identify key open research challenges at the intersection of AI and business processes. We hope that this emerging theme will spark engaging conversations at the RPA Forum.

cs.AI↗

arXiv2020

A Snooze-less User-Aware Notification System for Proactive Conversational Agents

The ubiquity of smart phones and electronic devices has placed a wealth of information at the fingertips of consumers as well as creators of digital content. This has led to millions of notifications being issued each second from alerts about posted YouTube videos to tweets, emails and personal messages. Adding work related notifications and we can see how quickly the number of notifications increases. Not only does this cause reduced productivity and concentration but has also been shown to cause alert fatigue. This condition makes users desensitized to notifications, causing them to ignore or miss important alerts. Depending on what domain users work in, the cost of missing a notification can vary from a mere inconvenience to life and death. Therefore, in this work, we propose an alert and notification framework that intelligently issues, suppresses and aggregates notifications, based on event severity, user preferences, or schedules, to minimize the need for users to ignore, or snooze their notifications and potentially forget about addressing important ones. Our framework can be deployed as a backend service, but is better suited to be integrated into proactive conversational agents, a field receiving a lot of attention with the digital transformation era, email services, news services and others. However, the main challenge lies in developing the right machine learning algorithms that can learn models from a wide set of users while customizing these models to individual users' preferences.

cs.HC↗