arXiv subjects

K. R. Jayaram

Publications and source records attributed to K. R. Jayaram.

17 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

Shift Happens: Mixture of Experts based Continual Adaptation in Federated Learning

Federated Learning (FL) enables collaborative model training across decentralized clients without sharing raw data, yet faces significant challenges in real-world settings where client data distributions evolve dynamically over time. This paper tackles the critical problem of covariate and label shifts in streaming FL environments, where non-stationary data distributions degrade model performance and necessitate a middleware layer that adapts FL to distributional shifts. We introduce ShiftEx, a shift-aware mixture of experts framework that dynamically creates and trains specialized global models in response to detected distribution shifts using Maximum Mean Discrepancy for covariate shifts. The framework employs a latent memory mechanism for expert reuse and implements facility location-based optimization to jointly minimize covariate mismatch, expert creation costs, and label imbalance. Through theoretical analysis and comprehensive experiments on benchmark datasets, we demonstrate 5.5-12.9 percentage point accuracy improvements and 22-95 % faster adaptation compared to state-of-the-art FL baselines across diverse shift scenarios. The proposed approach offers a scalable, privacy-preserving middleware solution for FL systems operating in non-stationary, real-world conditions while minimizing communication and computational overhead.

cs.LG↗

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

Performance of Confidential Computing GPUs

This work examines latency, throughput, and other metrics when performing inference on confidential GPUs. We explore different traffic patterns and scheduling strategies using a single Virtual Machine with one NVIDIA H100 GPU, to perform relaxed batch inferences on multiple Large Language Models (LLMs), operating under the constraint of swapping models in and out of memory, which necessitates efficient control. The experiments simulate diverse real-world scenarios by varying parameters such as traffic load, traffic distribution patterns, scheduling strategies, and Service Level Agreement (SLA) requirements. The findings provide insights into the differences between confidential and non-confidential settings when performing inference in scenarios requiring active model swapping. Results indicate that in No-CC mode, relaxed batch inference with model swapping latency is 20-30% lower than in confidential mode. Additionally, SLA attainment is 15-20% higher in No-CC settings. Throughput in No-CC scenarios surpasses that of confidential mode by 45-70%, and GPU utilization is approximately 50% higher in No-CC environments. Overall, performance in the confidential setting is inferior to that in the No-CC scenario, primarily due to the additional encryption and decryption overhead required for loading models onto the GPU in confidential environments.

cs.PF↗

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

FLIPS: Federated Learning using Intelligent Participant Selection

This paper presents the design and implementation of FLIPS, a middleware system to manage data and participant heterogeneity in federated learning (FL) training workloads. In particular, we examine the benefits of label distribution clustering on participant selection in federated learning. FLIPS clusters parties involved in an FL training job based on the label distribution of their data apriori, and during FL training, ensures that each cluster is equitably represented in the participants selected. FLIPS can support the most common FL algorithms, including FedAvg, FedProx, FedDyn, FedOpt and FedYogi. To manage platform heterogeneity and dynamic resource availability, FLIPS incorporates a straggler management mechanism to handle changing capacities in distributed, smart community applications. Privacy of label distributions, clustering and participant selection is ensured through a trusted execution environment (TEE). Our comprehensive empirical evaluation compares FLIPS with random participant selection, as well as three other "smart" selection mechanisms - Oort, TiFL and gradient clustering using two real-world datasets, two benchmark datasets, two different non-IID distributions and three common FL algorithms (FedYogi, FedProx and FedAvg). We demonstrate that FLIPS significantly improves convergence, achieving higher accuracy by 17 - 20 % with 20 - 60 % lower communication costs, and these benefits endure in the presence of straggler participants.

cs.LG↗

arXiv2022

Adaptive Aggregation For Federated Learning

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 many application domains. This increasing adoption has led to rapid growth in the number, size (number of participants/parties) and diversity (intermittent vs. active parties) of FL jobs. Many existing FL systems, based on centralized (often single) model aggregators are unable to scale to handle large FL jobs and adapt to parties' behavior. In this paper, we present a new scalable and adaptive architecture for FL aggregation. First, we demonstrate how traditional tree overlay based aggregation techniques (from P2P, publish-subscribe and stream processing research) can help FL aggregation scale, but are ineffective from a resource utilization and cost standpoint. Next, we present the design and implementation of AdaFed, which uses serverless/cloud functions to adaptively scale aggregation in a resource efficient and fault tolerant manner. We describe how AdaFed enables FL aggregation to be dynamically deployed only when necessary, elastically scaled to handle participant joins/leaves and is fault tolerant with minimal effort required on the (aggregation) programmer side. We also demonstrate that our prototype based on Ray scales to thousands of participants, and is able to achieve a >90% reduction in resource requirements and cost, with minimal impact on aggregation latency.

cs.DC↗

arXiv2022

Just-in-Time Aggregation for Federated Learning

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 aggregation work. Existing FL research has focused on the design of FL algorithms and optimization, and less on the efficacy of aggregation. Existing FL platforms often employ aggregators that actively wait for model updates. This wastes computational resources on the cloud, especially in large scale FL settings where parties are intermittently available for training. In this paper, we propose a new FL aggregation paradigm -- "just-in-time" (JIT) aggregation that leverages unique properties of FL jobs, especially the periodicity of model updates, to defer aggregation as much as possible and free compute resources for other FL jobs or other datacenter workloads. We describe a novel way to prioritize FL jobs for aggregation, and demonstrate using multiple datasets, models and FL aggregation algorithms that our techniques can reduce resource usage by 60+\% when compared to eager aggregation used in existing FL platforms. We also demonstrate that using JIT aggregation has negligible overhead and impact on the latency of the FL job.

cs.DC↗

arXiv2021

Separation of Powers in Federated Learning

Federated Learning (FL) enables collaborative training among mutually distrusting parties. Model updates, rather than training data, are concentrated and fused in a central aggregation server. A key security challenge in FL is that an untrustworthy or compromised aggregation process might lead to unforeseeable information leakage. This challenge is especially acute due to recently demonstrated attacks that have reconstructed large fractions of training data from ostensibly "sanitized" model updates. In this paper, we introduce TRUDA, a new cross-silo FL system, employing a trustworthy and decentralized aggregation architecture to break down information concentration with regard to a single aggregator. Based on the unique computational properties of model-fusion algorithms, all exchanged model updates in TRUDA are disassembled at the parameter-granularity and re-stitched to random partitions designated for multiple TEE-protected aggregators. Thus, each aggregator only has a fragmentary and shuffled view of model updates and is oblivious to the model architecture. Our new security mechanisms can fundamentally mitigate training reconstruction attacks, while still preserving the final accuracy of trained models and keeping performance overheads low.

cs.CR↗

arXiv2020

MYSTIKO : : Cloud-Mediated, Private, Federated Gradient Descent

Federated learning enables multiple, distributed participants (potentially on different clouds) to collaborate and train machine/deep learning models by sharing parameters/gradients. However, sharing gradients, instead of centralizing data, may not be as private as one would expect. Reverse engineering attacks on plaintext gradients have been demonstrated to be practically feasible. Existing solutions for differentially private federated learning, while promising, lead to less accurate models and require nontrivial hyperparameter tuning. In this paper, we examine the use of additive homomorphic encryption (specifically the Paillier cipher) to design secure federated gradient descent techniques that (i) do not require addition of statistical noise or hyperparameter tuning, (ii) does not alter the final accuracy or utility of the final model, (iii) ensure that the plaintext model parameters/gradients of a participant are never revealed to any other participant or third party coordinator involved in the federated learning job, (iv) minimize the trust placed in any third party coordinator and (v) are efficient, with minimal overhead, and cost effective.

cs.CR↗

arXiv2020

Effective Elastic Scaling of Deep Learning Workloads

The increased use of deep learning (DL) in academia, government and industry has, in turn, led to the popularity of on-premise and cloud-hosted deep learning platforms, whose goals are to enable organizations utilize expensive resources effectively, and to share said resources among multiple teams in a fair and effective manner. In this paper, we examine the elastic scaling of Deep Learning (DL) jobs over large-scale training platforms and propose a novel resource allocation strategy for DL training jobs, resulting in improved job run time performance as well as increased cluster utilization. We begin by analyzing DL workloads and exploit the fact that DL jobs can be run with a range of batch sizes without affecting their final accuracy. We formulate an optimization problem that explores a dynamic batch size allocation to individual DL jobs based on their scaling efficiency, when running on multiple nodes. We design a fast dynamic programming based optimizer to solve this problem in real-time to determine jobs that can be scaled up/down, and use this optimizer in an autoscaler to dynamically change the allocated resources and batch sizes of individual DL jobs. We demonstrate empirically that our elastic scaling algorithm can complete up to $\approx 2 \times$ as many jobs as compared to a strong baseline algorithm that also scales the number of GPUs but does not change the batch size. We also demonstrate that the average completion time with our algorithm is up to $\approx 10 \times$ faster than that of the baseline.

cs.DC↗

arXiv2019

FfDL : A Flexible Multi-tenant Deep Learning Platform

Deep learning (DL) is becoming increasingly popular in several application domains and has made several new application features involving computer vision, speech recognition and synthesis, self-driving automobiles, drug design, etc. feasible and accurate. As a result, large scale on-premise and cloud-hosted deep learning platforms have become essential infrastructure in many organizations. These systems accept, schedule, manage and execute DL training jobs at scale. This paper describes the design, implementation and our experiences with FfDL, a DL platform used at IBM. We describe how our design balances dependability with scalability, elasticity, flexibility and efficiency. We examine FfDL qualitatively through a retrospective look at the lessons learned from building, operating, and supporting FfDL; and quantitatively through a detailed empirical evaluation of FfDL, including the overheads introduced by the platform for various deep learning models, the load and performance observed in a real case study using FfDL within our organization, the frequency of various faults observed including unanticipated faults, and experiments demonstrating the benefits of various scheduling policies. FfDL has been open-sourced.

cs.DC↗

arXiv2019

Elastic Remote Methods

For distributed applications to take full advantage of cloud computing systems, we need middleware systems that allow developers to build elasticity management components right into the applications. This paper describes the design and implementation of ElasticRMI, a middleware system that (1) enables application developers to dynamically change the number of (server) objects available to handle remote method invocations with respect to the application's workload, without requiring major changes to clients (invokers) of remote methods, (2) enables flexible elastic scaling by allowing developers to use a combination of resource utilization metrics and fine-grained application-specific information like the properties of internal data structures to drive scaling decisions, (3) provides a high-level programming framework that handles elasticity at the level of classes and objects, masking low-level platform specific tasks (like provisioning VM images) from the developer, and (4) increases the portability of ElasticRMI applications across different private data centers/IaaS clouds through Apache Mesos.

cs.DC↗

arXiv2018

Dependability in a Multi-tenant Multi-framework Deep Learning as-a-Service Platform

Deep learning (DL), a form of machine learning, is becoming increasingly popular in several application domains. As a result, cloud-based Deep Learning as a Service (DLaaS) platforms have become an essential infrastructure in many organizations. These systems accept, schedule, manage and execute DL training jobs at scale. This paper explores dependability in the context of a DLaaS platform used in IBM. We begin by explaining how DL training workloads are different, and what features ensure dependability in this context. We then describe the architecture, design and implementation of a cloud-based orchestration system for DL training. We show how this system has been architected with dependability in mind while also being horizontally scalable, elastic, flexible and efficient. We also present an initial empirical evaluation of the overheads introduced by our platform, and discuss tradeoffs between efficiency and dependability.

cs.DC↗

arXiv2017

IBM Deep Learning Service

Deep learning driven by large neural network models is overtaking traditional machine learning methods for understanding unstructured and perceptual data domains such as speech, text, and vision. At the same time, the "as-a-Service"-based business model on the cloud is fundamentally transforming the information technology industry. These two trends: deep learning, and "as-a-service" are colliding to give rise to a new business model for cognitive application delivery: deep learning as a service in the cloud. In this paper, we will discuss the details of the software architecture behind IBM's deep learning as a service (DLaaS). DLaaS provides developers the flexibility to use popular deep learning libraries such as Caffe, Torch and TensorFlow, in the cloud in a scalable and resilient manner with minimal effort. The platform uses a distribution and orchestration layer that facilitates learning from a large amount of data in a reasonable amount of time across compute nodes. A resource provisioning layer enables flexible job management on heterogeneous resources, such as graphics processing units (GPUs) and central processing units (CPUs), in an infrastructure as a service (IaaS) cloud.

cs.DC↗