14 papers
ArchEval: Measuring AI Agents as Computer Architects
Chenyu Wang, Zishen Wan, Jeffrey Ma +8
Computer architecture has long used benchmarks to make progress measurable. LLM agents create a different measurement problem: success is not merely writing code or tuning paramete…
A Workflow-Aware Serving Layer for Agentic Applications
Jiayi Qian, Zishen Wan, Hanchen Yang +3
Agentic AI applications form an emerging serving workload in which a request creates a workflow: a directed acyclic graph of LLM and tool calls that exposes per-node model choices…
AgentDSE: Reasoning-Augmented Architectural Design Space Exploration
Chenyu Wang, Jiahe Caroline Shi, David Kong +4
Traditional architectural design space exploration (DSE) is highly inefficient, typically requiring tens of thousands of simulator evaluations across various optimization methods.…
FLARE: One-Shot PE-Level Fault Localization in Systolic Arrays via Algebraic Test Vectors
Logashree Venkatasubramanian, Zishen Wan, Viveck Cadambe
Systolic arrays are the dominant compute fabric for neural network inference. Prior work has addressed column-level fault detection efficiently with uniform test patterns, but row-…
Slm-mux: Orchestrating small language models for reasoning
Chenyu Wang, Zishen Wan, Hao Kang +5
With the rapid development of language models, the number of small language models (SLMs) has grown significantly. Although they do not achieve state-of-the-art accuracy, they are…
REASON: Accelerating Probabilistic Logical Reasoning for Scalable Neuro-Symbolic Intelligence
Zishen Wan, Che-Kai Liu, Jiayi Qian +3
Neuro-symbolic AI systems integrate neural perception with symbolic reasoning to enable data-efficient, interpretable, and robust intelligence beyond purely neural models. Although…