srimat t chakradhar Archives | NEC Labs America

Bifröst: Peer-to-peer Load-balancing for Function Execution in Agentic AI Systems

August 25, 2025/in Publications/by NEC Labs America

Agentic AI systems rely on Large Language Models (LLMs) to execute complex tasks by invoking external functions. The efficiency of these systems depends on how well function execution is managed, especially under heterogeneous and high-variance workloads, where function execution times can range from milliseconds to several seconds. Traditional load-balancing techniques, such as round-robin, least-loaded, and Peak-EWMA (used in Linkerd), struggle in such settings: round-robin ignores load imbalance, least-loaded reacts slowly to rapid workload shifts, and Peak-EWMA relies on latency tracking, which is ineffective for workloads with high execution time variability. In this paper, we introduce Bifröst, a peer-to-peer load-balancing mechanism that distributes function requests based on real-time active request count rather than latency estimates. Instead of relying on centralized load-balancers or client-side decisions, Bifröst enables function-serving pods to dynamically distribute load by comparing queue lengths and offloading requests accordingly. This avoids unnecessary overhead while ensuring better responsiveness under high-variance workloads. Our evaluation on open-vocabulary object detection, multi-modal understanding, and code generation workloads shows that Bifröst improves function completion time by up to 20% when processing 13,700 requests from 137 AI agents on a 32-node Kubernetes cluster, outperforming both OpenFaaS and OpenFaaS with Linkerd. In an AI-driven insurance claims processing workflow, Bifröst achieves up to 25% faster execution.

Roadside Multi-LiDAR Data Fusion for Enhanced Traffic Safety

August 3, 2025/in Publications/by NEC Labs America

Roadside LiDAR (Light Detection and Ranging) sensors promise safer and faster traffic management and vehicular operations. However, occlusion and small view angles are significant challenges to widespread use of roadside LiDARs. We consider fusing data from multiple LiDARs at a traffic intersection to better estimate traffic parameters than one can estimate from a single LiDAR. The key challenge is to calibrate multiple LiDARs both in time and space. The problem is more complex when heterogeneous sensors differ in resolution and are positioned arbitrarily on a traffic intersection.We propose a calibration technique to fuse multiple LiDARs. We show that our technique works on various data granularity and enables real-time analytics for roadside traffic monitoring. We evaluate on a large number of simulated traffic scenarios and show that fusion improves accuracy of vehicle counting and near-collision detection. We apply our algorithm on real traffic data and demonstrate utility in classifying vehicles and detecting occluded traffic participants.

XPF: Agentic AI System for Business Workflow Automation

July 20, 2025/in Publications/by NEC Labs America

In this paper, we propose a novel agentic AI system called XPF, which enables users to create “agents” using just natural language, where each agent is capable of executing complex, real-world business workflows in an accurate and reliable manner. XPF provides an interface to develop and iterate over the agent creation process and then deploy the agent in production when satisfactory results are produced consistently. The key components of XPF include: (a) planner, which leverages LLM to generate a step-by-step plan, which can further be edited by a human (b) compiler, which leverages LLM to compile the plan into a flow graph (c) executor, which handles distributed execution of the flow graph (using LLM, tools, RAG, etc.) on an underlying cluster and (d) verifier, which helps in verification of the output (through human generated tests or auto-generated tests using LLM). We develop five different agents using XPF and conduct experiments to evaluate one particular aspect i.e. difference in accuracy and reliability of the five agents with “human-generated” vs “auto-generated” plans. Our experiments show that we can get much more accurate and reliable response for a business workflow when step-by-step instructions (in natural language) are given by a human familiar with the workflow, rather than letting the LLM figure out the execution plan steps. In particular, we observe that “human-generated” plan almost always gives 100% accuracy whereas “auto-generated” plan almost never gives 100% accuracy. In terms of reliability, we observe through Rouge-L, Blue and Meteor scores, that the output from “human-generated” plan is much more reliable than “auto-generated” plan.

Re-ranking the Context for Multimodal Retrieval Augmented Generation

July 18, 2025/in Publications/by NEC Labs America

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face unique challenges: (i) the retrieval process may select irrelevant entries to user query (e.g., images, documents), and (ii) vision-language models or multi-modal language models like GPT-4o may hallucinate when processing these entries to generate RAG output. In this paper, we aim to address the first challenge, i.e, improving the selection of relevant context from the knowledge-base in retrieval phase of the multi-modal RAG. Specifically, we leverage the relevancy score (RS) measure designed in our previous work for evaluating the RAG performance to select more relevant entries in retrieval process. The retrieval based on embeddings, say CLIP-based embedding, and cosine similarity usually perform poorly particularly for multi-modal data. We show that by using a more advanced relevancy measure, one can enhance the retrieval process by selecting more relevant pieces from the knowledge-base and eliminate the irrelevant pieces from the context by adaptively selecting up-to-?? entries instead of fixed number of entries. Our evaluation using COCO dataset demonstrates significant enhancement in selecting relevant context and accuracy of the generated response.

SimCache: Similarity Caching for Efficient VLM-based Scene Understanding

June 11, 2025/in Publications/by NEC Labs America

Scene understanding systems analyze visual contexts by detecting objects, their attributes, and the interactions among them to provide a holistic interpretation. Understanding a scene requires analyzing multiple salient regions within a single video frame. Recently, Vision-Language Models (VLMs) have emerged as powerful tools for scene understanding, leveraging learned world knowledge to enable deployment without specialized training or fine-tuning. However, deploying VLMs in real-time applications is challenging due to their high computational and memory requirements, which limit processing throughput. We propose SimCache, a novel software-based caching mechanism that optimizes VLM-based scene understanding systems by reducing redundant computations. SimCache stores the embedding representation of a salient region and its detected activity, enabling reuse of VLM computations for similar regions in future frames. Specifically, SimCache exploits two types of redundancy: (1) temporal locality, reusing computations for similar regions across adjacent frames, and (2) semantic locality, reusing computations for visually distinct regions that represent the same activity at different times. SimCache includes a multi-tier cache architecture with specialized cache search and refinement policies to exploit redundancy efficiently and accurately. Experiments on action recognition datasets demonstrate that SimCache improves system throughput by up to 9.4× and reduces VLM computations by up to 24.4× with minimal accuracy loss.

Latency-driven Execution of LLM-generated Application Code on the Computing Continuum

May 19, 2025/in Publications/by NEC Labs America

Latency-critical applications demand quick responses. Ideally, detailed insights are preferable for the best decision making and response actions. However, in situations when detailed insights cannot be provided quickly, even basic information goes a long way in tackling the situation effectively. For example, in marine security application, it is critical to immediately notify as soon as an unauthorized vessel is seen. Hence, timely response may be prioritized over the response based on entire details. To address such latency-critical situations, in this paper, we propose a novel system called DiCE-EC, which leverages LLM to generate distributed code with speculative execution on Edge (fast and simple response using resource constrained hardware) and Cloud (detailed response using powerful hardware, but may be fast or slow depending on network conditions). DiCE-EC breaks down application into smaller components and executes them asynchronously across the edge and cloud computing continuum. As network conditions vary, we show through real-world marine security application, that DiCE-EC is effective in dynamically choosing detailed insights from cloud when received within latency-constraint, or falling back to simple response from edge to guarantee timely alert delivery. Without such dynamic selection of response from edge or cloud, existing systems either always provide simple responses or drop alerts. We perform real network measurements in the Gulf of Pozzuoli in Naples, Italy along accessible areas (inland and in a Ferry) and generate 1 million realistic measurements across four inaccessible regions, and demonstrate that DiCE-EC never misses an alert, while baseline misses up to ?4% alerts with real data and up to ?1% (10,000 alerts) with generated data.

LLM-based Distributed Code Generation and Cost-Efficient Execution in the Cloud

April 6, 2025/in Publications/by NEC Labs America

The advancement of Generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), is reshaping the software industry by automating code generation. Many LLM-driven distributed processing systems rely on serial code generation constrained by predefined libraries, limiting flexibility and adaptability. While some approaches enhance performance through parallel execution or optimize edge-cloud distributed processing for specific domains, they often overlook the cost implications of deployment, restricting scalability and economic feasibility across diverse cloud environments. This paper presents DiCE-C, a system that eliminates these constraints by starting directly from a natural language query. DiCE-C dynamically identifies available tools at runtime, programmatically refines LLM prompts, and employs a stepwise approachfirst generating serial code and then transforming it into distributed code. This adaptive methodology enables efficient distributed execution without dependence on specific libraries. By leveraging high-level parallelism at the Application Programming Interface (API) level and managing API execution as services within a Kubernetes-based runtime, DiCE-C reduces idle GPU time and facilitates the use of smaller, cost-effective GPU instances. Experiments with a vision-based insurance application demonstrate that DiCE-C reduces cloud operational costs by up to 72% when using smaller GPUs (A6000 and A4000 GPU machines vs. A100 GPU machine) and by 32% when using identical GPUs (A100 GPU machines). This flexible and cost-efficient approach makes DiCE-C a scalable solution for deploying LLM-generated vision applications in cloud environments.

Real-Time Network-Aware Roadside LiDAR Data Compression

April 2, 2025/in Publications/by NEC Labs America

LiDAR technology has emerged as a pivotal tool in Intelligent Transportation Systems (ITS), providing unique capabilities that have significantly transformed roadside traffic applications. However, this transformation comes with a distinct challenge: the immense volume of data generated by LiDAR sensors. These sensors produce vast amounts of data every second, which can overwhelm both private and public 5G networks that are used to connect intersections. This data volume makes it challenging to stream raw sensor data across multiple intersections effectively. This paper proposes an efficient real-time compression method for roadside LiDAR data. Our approach exploits a special characteristic of roadside LiDAR data: the background points are consistent across all frames. We detect these background points and send them to edge servers only once. For each subsequent frame, we filter out the background points and compress only the remaining data. This process achieves significant temporal compression by eliminating redundant background data and substantial spatial compression by focusing only on the filtered points. Our method is sensor-agnostic, exceptionally fast, memory-efficient, and adaptable to varying network conditions. It offers a 2.5x increase in compression rates and improves application-level accuracy by 40% compared to current state-of-the-art methods.

CAMTUNER: Adaptive Video Analytics Pipelines via Real-time Automated Camera Parameter Tuning

March 31, 2025/in Publications/by NEC Labs America

In Video Analytics Pipelines (VAP), Analytics Units (AUs) such as object detection and face recognition operating on remote servers rely heavily on surveillance cameras to capture high-quality video streams to achieve high accuracy. Modern network cameras offer an array of parameters that directly influence video quality. While a few of such parameters, e.g., exposure, focus and white balance, are automatically adjusted by the camera internally, the others are not. We denote such camera parameters as non-automated (NAUTO) parameters. In this work, we first show that in a typical surveillance camera deployment, environmental condition changes can have significant adverse effect on the accuracy of insights from the AUs, but such adverse impact can potentially be mitigated by dynamically adjusting NAUTO camera parameters in response to changes in environmental conditions. Second, since most end-users lack the skill or understanding to appropriately configure these parameters and typically use a fixed parameter setting, we present CAMTUNER, to our knowledge, the first framework that dynamically adapts NAUTO camera parameters to optimize the accuracy of AUs in a VAP in response to adverse changes in environmental conditions. CAMTUNER is based on SARSA reinforcement learning and it incorporates two novel components: a light-weight analytics quality estimator and a virtual camera that drastically speed up offline RL training. Our controlled experiments and real-world VAP deployment show that compared to a VAP using the default camera setting, CAMTUNER enhances VAP accuracy by detecting 15.9% additional persons and 2.6%-4.2% additional cars (without any false positives) in a large enterprise parking lot. CAMTUNER opens up new avenues for elevating video analytics accuracy, transcending mere incremental enhancements achieved through refining deep-learning models.

EdgeSync: Efficient Edge-Assisted Video Analytics via Network Contention-Aware Scheduling

March 17, 2025/in Publications/by NEC Labs America

With the advancement of 5G, edge-assisted video analytics has become increasingly popular, driven by the technologys ability to support low-latency, high-bandwidth applications. However, in scenarios where multiple clients competing for network resources, network contention poses a significant challenge. In this paper, we propose a novel scheduling algorithm that intelligently batches and aligns the offloading of multiple video analytics clients to optimize both network and edge server resource utilization while meeting the Service Level Objective (SLO). Experiment with a cellular network testbed shows that our approach successfully processes 93% or more of inference requests from 7 different clients to the edge server while meeting the SLOs, whereas other approaches achieve a lower success rate, ranging from 65% to 85% under the same condition.