arXiv subjects

Ankita Nayak

Publications and source records attributed to Ankita Nayak.

10 recordsLinked to original sources

arXiv2026

Agentic AI Workload Characteristics

Agentic AI shifts LLM serving from isolated prompt-generation requests to stateful, multi-turn executions that repeatedly invoke the model, call tools, and grow context over time. This paper characterizes ReAct-style agents from both the LLM-serving and tool-execution perspectives using an end-to-end tracing infrastructure across reasoning and non-reasoning Gemma and Qwen configurations on five agentic benchmarks. Our study shows that agentic workloads are not simply long-prompt workloads: with effective context caching, most input tokens are reused across turns, making execution decode-dominated while increasing dependence on long-lived KV-cache state. We also find that tool use has a clear temporal structure, with agents shifting from read/explore behavior early in execution to execute/write behavior later. These results show that efficient agentic serving must jointly manage repeated model re-entry, persistent context state, and workload-dependent tool behavior.

cs.DC↗

arXiv2026

QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture

The field of computer architecture, which bridges high-level software abstractions and low-level hardware implementations, remains absent from current large language model (LLM) evaluations. To this end, we present QuArch (pronounced 'quark'), the first benchmark designed to facilitate the development and evaluation of LLM knowledge and reasoning capabilities specifically in computer architecture. QuArch v1.0 provides a comprehensive collection of 2,671 expert-validated question-answer (QA) pairs covering various aspects of computer architecture, including processor design, memory systems, and interconnection networks. Our evaluation reveals that while frontier models possess domain-specific knowledge, they struggle with skills that require higher-order thinking in computer architecture. Frontier model accuracies vary widely (from 34% to 73%) on these advanced questions, highlighting persistent gaps in architectural reasoning across analysis, design, and implementation QAs. Furthermore, via fine-tuning we find that QuArch can translate to improved performance on a realistic memory hierarchy design task, resulting in up to 1.99x more area-efficient solutions and up to 40% more viable solutions overall. By holistically assessing fundamental skills, QuArch provides a foundation for building and measuring LLM capabilities that can accelerate innovation in computing systems. The QuArch benchmark and leaderboard are publicly available at: https://quarch.ai/.

cs.AR↗

arXiv2026

Efficient Reasoning on the Edge

Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large context requirements make them impractical for edge deployment. These challenges include high token generation costs, large KV-cache footprints, and inefficiencies when distilling reasoning capabilities into smaller models for mobile devices. Existing approaches often rely on distilling reasoning traces from larger models into smaller models, which are verbose and stylistically redundant, undesirable for on-device inference. In this work, we propose a lightweight approach to enable reasoning in small LLMs using LoRA adapters combined with supervised fine-tuning. We further introduce budget forcing via reinforcement learning on these adapters, significantly reducing response length with minimal accuracy loss. To address memory-bound decoding, we exploit parallel test-time scaling, improving accuracy at minor latency increase. Finally, we present a dynamic adapter-switching mechanism that activates reasoning only when needed and a KV-cache sharing strategy during prompt encoding, reducing time-to-first-token for on-device inference. Experiments on Qwen2.5-7B demonstrate that our method achieves efficient, accurate reasoning under strict resource constraints, making LLM reasoning practical for mobile scenarios. Videos demonstrating our solution running on mobile devices are available on our project page.

cs.LG↗

arXiv2026

Video Reasoning without Training

Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought, resulting in substantial computational overhead during both training and inference. Moreover, the mechanisms that control the thinking process in these reasoning models are very limited. In this paper, we use the entropy of the model's output distribution as a signal to study and guide reasoning behavior. We discover that high-quality models exhibit a characteristic pattern of micro-exploration and micro-exploitation cycles, followed by a later entropy peak (i.e., longer thinking) and a lower final entropy, indicating more deliberate exploration and confident convergence (i.e., avoid excessive randomness while the model is exploring or thinking through an answer). We then use these novel, theoretically-grounded insights to introduce V-Reason (Video-Reason), an inference-time optimization method that adapts the value cache of the LMM through a lightweight, trainable controller. Our proposed controller is guided by an entropy-based objective, to tune the model's behavior directly at inference, without using any RL or supervised fine-tuning. Our experiments show that V-Reason significantly outperforms the base instruction-tuned models on many video reasoning datasets, narrowing the gap with RL models to within 0.6% accuracy on average. We achieve this without any training, while offering efficiency benefits: V-Reason uses 58.6% fewer tokens than the RL model. Project Page https://deepaksridhar.github.io/vreason.github.io/

cs.CV↗

arXiv2026

KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators

Production inference increasingly targets a heterogeneous mix of accelerators. Agentic pipelines interleave reasoning, tool calls, and multi-agent coordination, each with distinct compute and memory profiles. For optimal efficiency, each stage should run on the accelerator best suited to it. This creates a systems challenge: each pipeline now requires high-performance kernels across a growing set of hardware backends and programming models. Writing these kernels by hand is time-consuming, demands deep low-level expertise, and does not scale as kernel complexity grows. Recently, Large Language Models (LLMs) have been leveraged for automatic kernel generation, but challenges in low-level code generation and cross-backend generalization persist. We present KForge, a cross-platform framework built around an iterative refinement loop driven by two collaborating LLM-based agents: a generation agent that produces and progressively refines kernels using compilation and correctness feedback, and a performance-analysis agent that interprets profiling data, from programmatic APIs to GUI-based tools, and emits recommendations that steer the next round of synthesis. The loop alternates between functional passes, which drive a candidate to correctness, and optimization passes, which close the performance gap to hand-tuned baselines. We evaluate KForge on two backends with very different baseline reference availability. On NVIDIA B200, KForge achieves a 2.12$\%$ improvement in end-to-end throughput compared to TensorRT-LLM on the gpt-oss-20b inference speed benchmark. On Intel Arc B580, KForge generates Triton kernels achieving a 5.13$\times$ geometric mean speedup over the faster of PyTorch eager and torch.compile on 37 GEMM + tail-ops workloads from KernelBench Level 2, primarily via operator fusion and mixed-precision execution.

cs.LG↗

arXiv2025

DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization

We tackle the challenge of jointly personalizing content and style from a few examples. A promising approach is to train separate Low-Rank Adapters (LoRA) and merge them effectively, preserving both content and style. Existing methods, such as ZipLoRA, treat content and style as independent entities, merging them by learning masks in LoRA's output dimensions. However, content and style are intertwined, not independent. To address this, we propose DuoLoRA, a content-style personalization framework featuring three key components: (i) rank-dimension mask learning, (ii) effective merging via layer priors, and (iii) Constyle loss, which leverages cycle-consistency in the merging process. First, we introduce ZipRank, which performs content-style merging within the rank dimension, offering adaptive rank flexibility and significantly reducing the number of learnable parameters. Additionally, we incorporate SDXL layer priors to apply implicit rank constraints informed by each layer's content-style bias and adaptive merger initialization, enhancing the integration of content and style. To further refine the merging process, we introduce Constyle loss, which leverages the cycle-consistency between content and style. Our experimental results demonstrate that DuoLoRA outperforms state-of-the-art content-style merging methods across multiple benchmarks.

cs.GR↗

arXiv2025

SubZero: Composing Subject, Style, and Action via Zero-Shot Personalization

Diffusion models are increasingly popular for generative tasks, including personalized composition of subjects and styles. While diffusion models can generate user-specified subjects performing text-guided actions in custom styles, they require fine-tuning and are not feasible for personalization on mobile devices. Hence, tuning-free personalization methods such as IP-Adapters have progressively gained traction. However, for the composition of subjects and styles, these works are less flexible due to their reliance on ControlNet, or show content and style leakage artifacts. To tackle these, we present SubZero, a novel framework to generate any subject in any style, performing any action without the need for fine-tuning. We propose a novel set of constraints to enhance subject and style similarity, while reducing leakage. Additionally, we propose an orthogonalized temporal aggregation scheme in the cross-attention blocks of denoising model, effectively conditioning on a text prompt along with single subject and style images. We also propose a novel method to train customized content and style projectors to reduce content and style leakage. Through extensive experiments, we show that our proposed approach, while suitable for running on-edge, shows significant improvements over state-of-the-art works performing subject, style and action composition.

cs.CV↗

arXiv2025

QuArch: A Question-Answering Dataset for AI Agents in Computer Architecture

We introduce QuArch, a dataset of 1500 human-validated question-answer pairs designed to evaluate and enhance language models' understanding of computer architecture. The dataset covers areas including processor design, memory systems, and performance optimization. Our analysis highlights a significant performance gap: the best closed-source model achieves 84% accuracy, while the top small open-source model reaches 72%. We observe notable struggles in memory systems, interconnection networks, and benchmarking. Fine-tuning with QuArch improves small model accuracy by up to 8%, establishing a foundation for advancing AI-driven computer architecture research. The dataset and leaderboard are at https://harvard-edge.github.io/QuArch/.

cs.AR↗

arXiv2021

Enabling Reusable Physical Design Flows with Modular Flow Generators

Achieving high code reuse in physical design flows is challenging but increasingly necessary to build complex systems. Unfortunately, existing approaches based on parameterized Tcl generators support very limited reuse and struggle to preserve reusable code as designers customize flows for specific designs and technologies. We present a vision and framework based on modular flow generators that encapsulates coarse-grain and fine-grain reusable code in modular nodes and assembles them into complete flows. The key feature is a flow consistency and instrumentation layer embedded in Python, which supports mechanisms for rapid and early feedback on inconsistent composition. The approach gradually types the Tcl language and allows both automatic and user-annotated static assertion checks. We evaluate the design flows of successive generations of silicon prototypes designed in TSMC16, TSMC28, TSMC40, SKY130, and IBM180 technologies, showing how our approach can enable significant code reuse in future flows.

cs.AR↗

arXiv2020

Interstellar: Using Halide's Scheduling Language to Analyze DNN Accelerators

We show that DNN accelerator micro-architectures and their program mappings represent specific choices of loop order and hardware parallelism for computing the seven nested loops of DNNs, which enables us to create a formal taxonomy of all existing dense DNN accelerators. Surprisingly, the loop transformations needed to create these hardware variants can be precisely and concisely represented by Halide's scheduling language. By modifying the Halide compiler to generate hardware, we create a system that can fairly compare these prior accelerators. As long as proper loop blocking schemes are used, and the hardware can support mapping replicated loops, many different hardware dataflows yield similar energy efficiency with good performance. This is because the loop blocking can ensure that most data references stay on-chip with good locality and the processing units have high resource utilization. How resources are allocated, especially in the memory system, has a large impact on energy and performance. By optimizing hardware resource allocation while keeping throughput constant, we achieve up to 4.2X energy improvement for Convolutional Neural Networks (CNNs), 1.6X and 1.8X improvement for Long Short-Term Memories (LSTMs) and multi-layer perceptrons (MLPs), respectively.

cs.DC↗