Related papers: LEGO: An LLM Skill-Based Front-End Design Generati…

We describe LEGO, a new approach to optimizing data movement whereby code is expressed as a layout-independent computation and composed with layouts for data and computation. This code generator organization derives complex indexing…

Large Language Models (LLMs) are driving a shift towards intent-driven development, where agents build complete software from scratch. However, existing benchmarks fail to assess this 0-to-1 generation capability due to two limitations:…

Large Language Models (LLMs) can generate Computer-Aided Design (CAD), yet lack physical comprehension required for reliable engineering design. Instead of attempting to implicitly learn physical laws from data, we propose a Hybrid…

Generative AI has made rapid advancements in recent years, achieving unprecedented capabilities in multimodal understanding and code generation. This can enable a new paradigm of front-end development in which multimodal large language…

LLMs have recently demonstrated strong capabilities in automatic RTL code generation, achieving high syntactic and functional correctness. However, most methods focus on functional correctness while overlooking critical physical design…

As hardware design complexity escalates, there is an urgent need for advanced automation in electronic design automation (EDA). Traditional register transfer level (RTL) design methods are manual, time-consuming, and prone to errors. While…

Large language models (LLMs) have improved Verilog generation from natural-language specifications, but most pipelines still treat generation as isolated sampling followed by functional checking. This is insufficient for practical RTL…

Multi-step spatial reasoning entails understanding and reasoning about spatial relationships across multiple sequential steps, which is crucial for tackling complex real-world applications, such as robotic manipulation, autonomous…

We propose LLM-Interleaved (LLM-I), a flexible and dynamic framework that reframes interleaved image-text generation as a tool-use problem. LLM-I is designed to overcome the "one-tool" bottleneck of current unified models, which are limited…

With the growing complexity of modern integrated circuits, hardware engineers are required to devote more effort to the full design-to-manufacturing workflow. This workflow involves numerous iterations, making it both labor-intensive and…

We propose a synthetic reasoning task, LEGO (Learning Equality and Group Operations), that encapsulates the problem of following a chain of reasoning, and we study how the Transformer architectures learn this task. We pay special attention…

Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edge-assisted…

Agent skills extend large language model (LLM) agents with reusable, program-like modules that define triggering conditions, procedural logic, and tool interactions. As these skills proliferate in public marketplaces, it is unclear what…

Next-generation edge intelligence is anticipated to benefit various applications via offloading techniques. However, traditional offloading architectures face several issues, including heterogeneous constraints, partial perception,…

Large language models (LLMs) have made rapid advancements in code generation for popular languages such as Python and C++. Many of these recent gains can be attributed to the use of ``agents'' that wrap domain-relevant tools alongside LLMs.…

Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grained spatial reasoning and precise object state detection are required. In this work, we…

Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative…

The performance of machine learning models on tabular data is critically dependent on high-quality feature engineering. While Large Language Models (LLMs) have shown promise in automating feature extraction (AutoFE), existing methods are…

AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant ones, degrades performance. As community-driven skill repositories grow,…

Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-code human priors about what to store and how to revise memory, making them…