arXiv subjects

Aditya Akella

Publications and source records attributed to Aditya Akella.

At least 37 records · Page 2Linked to original sources

arXiv2026

Software-Defined Agentic Serving

As multi-agent LLM pipelines grow in complexity, existing serving paradigms fail to adapt to the dynamic serving conditions. We argue that agentic serving systems should be programmable and system-aware, unlike existing serving which statically encode the parameters. In this work, we propose a new SDN-inspired agentic serving framework that helps control the key attributes of communication based on runtime state. This architecture enables serving-efficient, responsive agent systems and paves the way for high-level intent-driven agentic serving.

cs.DC↗

arXiv2025

SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling

Diffusion models have recently achieved remarkable success in generative tasks (e.g., image and video generation), and the demand for high-quality content (e.g., 2K/4K videos) is rapidly increasing across various domains. However, generating ultra-high-resolution videos on existing standard-resolution (e.g., 720p) platforms remains challenging due to the excessive re-training requirements and prohibitively high computational and memory costs. To this end, we introduce SUPERGEN, an efficient tile-based framework for ultra-high-resolution video generation. SUPERGEN features a novel training-free algorithmic innovation with tiling to successfully support a wide range of resolutions without additional training efforts while significantly reducing both memory footprint and computational complexity. Moreover, SUPERGEN incorporates a tile-tailored, adaptive, region-aware caching strategy that accelerates video generation by exploiting redundancy across denoising steps and spatial regions. SUPERGEN also integrates cache-guided, communication-minimized tile parallelism for enhanced throughput and minimized latency. Evaluations show that SUPERGEN maximizes performance gains while achieving high output quality across various benchmarks.

cs.LG↗

arXiv2025

Continuous Benchmark Generation for Evaluating Enterprise-scale LLM Agents

The rapid adoption of AI agents across domains has made systematic evaluation crucial for ensuring their usefulness and successful production deployment. Evaluation of AI agents typically involves using a fixed set of benchmarks and computing multiple evaluation metrics for the agent. While sufficient for simple coding tasks, these benchmarks fall short for enterprise-scale agents, where services and requirements evolve continuously and ground-truth examples are sparse. We propose a process of benchmark generation that helps evolve the benchmarks as the requirements change and perform robust evaluation of evolving AI agents. We instantiate this approach for a case study of service migration from one deployment platform to another at a large public enterprise. Our approach relies on semi-structured documents where developers express the high-level intent, and uses state-of-the-art LLMs to generate benchmarks from just a small number of such documents. Overall, this process results in a maintainable evaluation framework, enabling rapid feedback on agent performance and facilitating targeted improvements.

cs.SE↗

arXiv2025

Sherlock: Reliable and Efficient Agentic Workflow Execution

With the increasing adoption of large language models (LLM), agentic workflows, which compose multiple LLM calls with tools, retrieval, and reasoning steps, are increasingly replacing traditional applications. However, such workflows are inherently error-prone: incorrect or partially correct output at one step can propagate or even amplify through subsequent stages, compounding the impact on the final output. Recent work proposes integrating verifiers that validate LLM output or actions, such as self-reflection, debate, or LLM-as-a-judge mechanisms. Yet, verifying every step introduces significant latency and cost overheads. In this work, we seek to answer three key questions: which nodes in a workflow are most error-prone and thus deserve costly verification, how to select the most appropriate verifier for each node, and how to use verification with minimal impact to latency? Our solution, Sherlock, addresses these using counterfactual analysis on agentic workflows to identify error-prone nodes and selectively attaching cost-optimal verifiers only where necessary. At runtime, Sherlock speculatively executes downstream tasks to reduce latency overhead, while verification runs in the background. If verification fails, execution is rolled back to the last verified output. Compared to the non-verifying baseline, Sherlock delivers an 18.3% accuracy gain on average across benchmarks. Sherlock reduces workflow execution time by up to 48.7% over non-speculative execution and lowers verification cost by 26.0% compared to the Monte Carlo search-based method, demonstrating that principled, fault-aware verification effectively balances efficiency and reliability in agentic workflows.

cs.MA↗

arXiv2025

On the Fundamental Limitations of Decentralized Learnable Reward Shaping in Cooperative Multi-Agent Reinforcement Learning

Recent advances in learnable reward shaping have shown promise in single-agent reinforcement learning by automatically discovering effective feedback signals. However, the effectiveness of decentralized learnable reward shaping in cooperative multi-agent settings remains poorly understood. We propose DMARL-RSA, a fully decentralized system where each agent learns individual reward shaping, and evaluate it on cooperative navigation tasks in the simple_spread_v3 environment. Despite sophisticated reward learning, DMARL-RSA achieves only -24.20 +/- 0.09 average reward, compared to MAPPO with centralized training at 1.92 +/- 0.87 -- a 26.12-point gap. DMARL-RSA performs similarly to simple independent learning (IPPO: -23.19 +/- 0.96), indicating that advanced reward shaping cannot overcome fundamental decentralized coordination limitations. Interestingly, decentralized methods achieve higher landmark coverage (0.888 +/- 0.029 for DMARL-RSA, 0.960 +/- 0.045 for IPPO out of 3 total) but worse overall performance than centralized MAPPO (0.273 +/- 0.008 landmark coverage) -- revealing a coordination paradox between local optimization and global performance. Analysis identifies three critical barriers: (1) non-stationarity from concurrent policy updates, (2) exponential credit assignment complexity, and (3) misalignment between individual reward optimization and global objectives. These results establish empirical limits for decentralized reward learning and underscore the necessity of centralized coordination for effective multi-agent cooperation.

cs.MA↗

arXiv2025

A Joint Learning Approach to Hardware Caching and Prefetching

Several learned policies have been proposed to replace heuristics for scheduling, caching, and other system components in modern systems. By leveraging diverse features, learning from historical trends, and predicting future behaviors, such models promise to keep pace with ever-increasing workload dynamism and continuous hardware evolution. However, policies trained in isolation may still achieve suboptimal performance when placed together. In this paper, we inspect one such instance in the domain of hardware caching -- for the policies of cache replacement and prefetching. We argue that these two policies are bidirectionally interdependent and make the case for training the two jointly. We propose a joint learning approach based on developing shared representations for the features used by the two policies. We present two approaches to develop these shared representations, one based on a joint encoder and another based on contrastive learning of the embeddings, and demonstrate promising preliminary results for both of these. Finally, we lay down an agenda for future research in this direction.

cs.LG↗

arXiv2025

Man-Made Heuristics Are Dead. Long Live Code Generators!

Policy design for various systems controllers has conventionally been a manual process, with domain experts carefully tailoring heuristics for the specific instance in which the policy will be deployed. In this paper, we re-imagine policy design via a novel automated search technique fueled by recent advances in generative models, specifically Large Language Model (LLM)-driven code generation. We outline the design and implementation of PolicySmith, a framework that applies LLMs to synthesize instance-optimal heuristics. We apply PolicySmith to two long-standing systems policies - web caching and congestion control, highlighting the opportunities unraveled by this LLM-driven heuristic search. For caching, PolicySmith discovers heuristics that outperform established baselines on standard open-source traces. For congestion control, we show that PolicySmith can generate safe policies that integrate directly into the Linux kernel.

cs.OS↗

arXiv2025

Large Language Models as Realistic Microservice Trace Generators

Workload traces are essential to understand complex computer systems' behavior and manage processing and memory resources. Since real-world traces are hard to obtain, synthetic trace generation is a promising alternative. This paper proposes a first-of-a-kind approach that relies on training a large language model (LLM) to generate synthetic workload traces, specifically microservice call graphs. To capture complex and arbitrary hierarchical structures and implicit constraints in such traces, we propose to train LLMs to generate recursively, making call graph generation a sequence of more manageable steps. To further enforce learning constraints on the traces and generate uncommon situations, we apply additional instruction tuning steps to align our model with the desired trace features. With this method, we train TraceLLM, an LLM for microservice trace generation, and demonstrate that it produces diverse, realistic traces under varied conditions, outperforming existing approaches in both accuracy and validity. The synthetically generated traces can effectively replace real data to optimize important microservice management tasks. Additionally, TraceLLM adapts to downstream trace-related tasks, such as predicting key trace features and infilling missing data.

cs.SE↗

arXiv2025

Comparative Analysis of Time Series Foundation Models for Demographic Forecasting: Enhancing Predictive Accuracy in US Population Dynamics

Demographic shifts, influenced by globalization, economic conditions, geopolitical events, and environmental factors, pose significant challenges for policymakers and researchers. Accurate demographic forecasting is essential for informed decision-making in areas such as urban planning, healthcare, and economic policy. This study explores the application of time series foundation models to predict demographic changes in the United States using datasets from the U.S. Census Bureau and Federal Reserve Economic Data (FRED). We evaluate the performance of the Time Series Foundation Model (TimesFM) against traditional baselines including Long Short-Term Memory (LSTM) networks, Autoregressive Integrated Moving Average (ARIMA), and Linear Regression. Our experiments across six demographically diverse states demonstrate that TimesFM achieves the lowest Mean Squared Error (MSE) in 86.67% of test cases, with particularly strong performance on minority populations with sparse historical data. These findings highlight the potential of pre-trained foundation models to enhance demographic analysis and inform proactive policy interventions without requiring extensive task-specific fine-tuning.

cs.LG↗

arXiv2025

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they often degrade accuracy due to overemphasizing recent tokens. In this work, we first propose dual-state linear attention (DSLA), a novel design that maintains two specialized hidden states-one for preserving historical context and one for tracking recency-thereby mitigating the short-range bias typical of linear-attention architectures. To further balance efficiency and accuracy under dynamic workload conditions, we introduce DSLA-Serve, an online adaptive distillation framework that progressively replaces Transformer layers with DSLA layers at inference time, guided by a sensitivity-based layer ordering. DSLA-Serve uses a chained fine-tuning strategy to ensure that each newly converted DSLA layer remains consistent with previously replaced layers, preserving the overall quality. Extensive evaluations on commonsense reasoning, long-context QA, and text summarization demonstrate that DSLA-Serve yields 2.3x faster inference than Llama2-7B and 3.0x faster than the hybrid Zamba-7B, while retaining comparable performance across downstream tasks. Our ablation studies show that DSLA's dual states capture both global and local dependencies, addressing the historical-token underrepresentation seen in prior linear attentions. Codes are available at https://github.com/utnslab/DSLA-Serve.

cs.LG↗

arXiv2025

HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training

Training large language models (LLMs) increasingly relies on geographically distributed accelerators, causing prohibitive communication costs across regions and uneven utilization of heterogeneous hardware. We propose HALoS, a hierarchical asynchronous optimization framework that tackles these issues by introducing local parameter servers (LPSs) within each region and a global parameter server (GPS) that merges updates across regions. This hierarchical design minimizes expensive inter-region communication, reduces straggler effects, and leverages fast intra-region links. We provide a rigorous convergence analysis for HALoS under non-convex objectives, including theoretical guarantees on the role of hierarchical momentum in asynchronous training. Empirically, HALoS attains up to 7.5x faster convergence than synchronous baselines in geo-distributed LLM training and improves upon existing asynchronous methods by up to 2.1x. Crucially, HALoS preserves the model quality of fully synchronous SGD-matching or exceeding accuracy on standard language modeling and downstream benchmarks-while substantially lowering total training time. These results demonstrate that hierarchical, server-side update accumulation and global model merging are powerful tools for scalable, efficient training of new-era LLMs in heterogeneous, geo-distributed environments.

cs.LG↗

arXiv2025

CONGO: Compressive Online Gradient Optimization

We address the challenge of zeroth-order online convex optimization where the objective function's gradient exhibits sparsity, indicating that only a small number of dimensions possess non-zero gradients. Our aim is to leverage this sparsity to obtain useful estimates of the objective function's gradient even when the only information available is a limited number of function samples. Our motivation stems from the optimization of large-scale queueing networks that process time-sensitive jobs. Here, a job must be processed by potentially many queues in sequence to produce an output, and the service time at any queue is a function of the resources allocated to that queue. Since resources are costly, the end-to-end latency for jobs must be balanced with the overall cost of the resources used. While the number of queues is substantial, the latency function primarily reacts to resource changes in only a few, rendering the gradient sparse. We tackle this problem by introducing the Compressive Online Gradient Optimization framework which allows compressive sensing methods previously applied to stochastic optimization to achieve regret bounds with an optimal dependence on the time horizon without the full problem dimension appearing in the bound. For specific algorithms, we reduce the samples required per gradient estimate to scale with the gradient's sparsity factor rather than its full dimensionality. Numerical simulations and real-world microservices benchmarks demonstrate CONGO's superiority over gradient descent approaches that do not account for sparsity.

cs.LG↗

arXiv2025

ConfigBot: Adaptive Resource Allocation for Robot Applications in Dynamic Environments

The growing use of service robots in dynamic environments requires flexible management of on-board compute resources to optimize the performance of diverse tasks such as navigation, localization, and perception. Current robot deployments often rely on static OS configurations and system over-provisioning. However, they are suboptimal because they do not account for variations in resource usage. This results in poor system-wide behavior such as robot instability or inefficient resource use. This paper presents ConifgBot, a novel system designed to adaptively reconfigure robot applications to meet a predefined performance specification by leveraging \emph{runtime profiling} and \emph{automated configuration tuning}. Through experiments on multiple real robots, each running a different stack with diverse performance requirements, which could be \emph{context}-dependent, we illustrate ConifgBot's efficacy in maintaining system stability and optimizing resource allocation. Our findings highlight the promise of automatic system configuration tuning for robot deployments, including adaptation to dynamic changes.

cs.RO↗

arXiv2025

Speculative Ad-hoc Querying

Analyzing large datasets requires responsive query execution, but executing SQL queries on massive datasets can be slow. This paper explores whether query execution can begin even before the user has finished typing, allowing results to appear almost instantly. We propose SpeQL, a system that leverages Large Language Models (LLMs) to predict likely queries based on the database schema, the user's past queries, and their incomplete query. Since exact query prediction is infeasible, SpeQL speculates on partial queries in two ways: 1) it predicts the query structure to compile and plan queries in advance, and 2) it precomputes smaller temporary tables that are much smaller than the original database, but are still predicted to contain all information necessary to answer the user's final query. Additionally, SpeQL continuously displays results for speculated queries and subqueries in real time, aiding exploratory analysis. A utility/user study showed that SpeQL improved task completion time, and participants reported that its speculative display of results helped them discover patterns in the data more quickly. In the study, SpeQL improves user's query latency by up to $289\times$ and kept the overhead reasonable, at $\$4$ per hour.

cs.DB↗

arXiv2025

EdgeSight: Enabling Modeless and Cost-Efficient Inference at the Edge

Traditional ML inference is evolving toward modeless inference, which abstracts the complexity of model selection from users, allowing the system to automatically choose the most appropriate model for each request based on accuracy and resource requirements. While prior studies have focused on modeless inference within data centers, this paper tackles the pressing need for cost-efficient modeless inference at the edge -- particularly within its unique constraints of limited device memory, volatile network conditions, and restricted power consumption. To overcome these challenges, we propose EdgeSight, a system that provides cost-efficient EdgeSight serving for diverse DNNs at the edge. EdgeSight employs an edge-data center (edge-DC) architecture, utilizing confidence scaling to reduce the number of model options while meeting diverse accuracy requirements. Additionally, it supports lossy inference in volatile network environments. Our experimental results show that EdgeSight outperforms existing systems by up to 1.6x in P99 latency for modeless services. Furthermore, our FPGA prototype demonstrates similar performance at certain accuracy levels, with a power consumption reduction of up to 3.34x.

eess.SY↗

arXiv2024

SYMPHONY: Improving Memory Management for LLM Inference Workloads

Large Language Models (LLMs) are increasingly being deployed in applications such as chatbots, code editors, and conversational agents. A key feature of LLMs is their ability to engage in multi-turn interactions with humans or external tools, enabling a wide range of tasks. Each new request in a multi-turn interaction depends on the intermediate state, specifically the key-value (K,V) caches, from previous requests in the ongoing interaction. Existing serving engines either recompute the K,V caches or offload them to main memory. Profiling reveals that recomputation can result in over 99% of processed tokens being redundant. On the other hand, offloading K,V caches from GPU memory makes inference serving stateful, leading to load imbalances across the cluster. To address these challenges, we developed SYMPHONY. SYMPHONY leverages the observation that multi-turn work loads provide additional hints that allow K,V caches to be migrated off the critical serving path. By utilizing these hints, SYMPHONY dynamically migrates K,V caches to enable finegrained scheduling of inference requests. Our experiments demonstrate that SYMPHONY can handle over 8x the number of requests compared to state-of-the-art baselines, with a similar latency profile.

cs.DC↗

arXiv2024

Do Data Center Network Metrics Predict Application-Facing Performance?

Applications that run in large-scale data center networks (DCNs) rely on the DCN's ability to deliver application requests in a performant manner. DCNs expose a complex design and operational space, and network designers and operators care how different options along this space affect application performance. One might run controlled experiments and measure the corresponding application-facing performance, but such experiments become progressively infeasible at a large scale, and simulations risk yielding inaccurate or incomplete results. Instead, we show that we can predict application-facing performance through more easily measured network metrics. For example, network telemetry metrics (e.g., link utilization) can predict application-facing metrics (e.g., transfer latency). Through large-scale measurements of production networks, we study the correlation between the two types of metrics, and construct predictive, interpretable models that serve as a suggestive guideline to network designers and operators. We show that no single network metric is universally the best predictor (even though some prior work has focused on a single predictor). We found that simple linear models often have the lowest error, while queueing-based models are better in a few cases.

cs.NI↗

arXiv2024

Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design

The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved efficiency and performance. Despite their benefits, MoE models face significant challenges during inference, including inefficient memory management and suboptimal batching, due to misaligned design choices between the model architecture and the system policies. Furthermore, the conventional approach of training MoEs from scratch is increasingly prohibitive in terms of cost. In this paper, we propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models (in contrast to "upcycling" generalist MoEs), avoiding the high costs of ground-up training. Our approach employs activation sparsity to extract experts. To compose experts, we examine the widely-adopted layer-wise router design and show its redundancy, and thus we introduce the pre-gating router decoupled from the MoE backbone that facilitates system-friendly pre-computing and lookahead scheduling, enhancing expert-aware batching and caching. Our codesign therefore addresses critical gaps on both the algorithmic and system fronts, establishing a scalable and efficient alternative for LLM inference in resource-constrained settings. Read-ME outperforms other popular open-source dense models of similar scales, achieving improvements of up to 10.1% on MMLU, and improving mean end-to-end latency up to 6.1%. Codes are available at: https://github.com/VITA-Group/READ-ME.

cs.CL↗