Just created a new video using Avatars to demo Gemini and HAgent to extend a RISC-V Dino core with the B extension. youtu.be/DMT0Xz_-U5g

🎉 Proud to be one of 70 Amazon Research Award recipients this year! Great news for my students' funding too. Thanks Amazon for supporting academic research! www.amazon.science/research-awa...

arxiv 📄 μRL: Discovering Transient Execution Vulnerabilities Using Reinforcement Learning http://arxiv.org/abs/2502.14307v1 We propose using reinforcement learning to address the challenges of discovering microarchitectural vulnerabilities, such as Spectre and Meltdown, which exploit subtle int...

arxiv 📄 VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework http://arxiv.org/abs/2501.13411v1 Penetration testing is a vital practice for identifying and mitigating vulnerabilities in cybersecurity systems, but its manual execution is labor-intensive and time-consu...

arxiv 📄 MARL-OT: Multi-Agent Reinforcement Learning Guided Online Fuzzing to Detect Safety Violation in Autonomous Driving Systems http://arxiv.org/abs/2501.14451v1 Autonomous Driving Systems (ADSs) are safety-critical, as real-world safety violations can result in significant losses. Rigorous ...

arxiv 📄 Evaluating Agent-based Program Repair at Google http://arxiv.org/abs/2501.07531v1 Agent-based program repair offers to automatically resolve complex bugs end-to-end by combining the planning, tool use, and code generation abilities of modern LLMs. Recent work has explored the use of age...

arxiv 📄 Enabling New HDLs with Agents http://arxiv.org/abs/2501.00642v1 Large Language Models (LLMs) based agents are transforming the programming language landscape by facilitating learning for beginners, enabling code generation, and optimizing documentation workflows. Hardware Description La...

The new O3 ARC results are a new "oh shit moment" like the first time that I tried BERT or GPT-3. www.youtube.com/watch?v=duQu... going for a walk to think....

arxiv 📄 Design choices made by LLM-based test generators prevent them from finding bugs http://arxiv.org/abs/2412.14137v1 There is an increasing amount of research and commercial tools for automated test case generation using Large Language Models (LLMs). This paper critically examines whether ...

arxiv 📄 GHIssuemarket: A Sandbox Environment for SWE-Agents Economic Experimentation http://arxiv.org/abs/2412.11722v2 Software engineering agents (swe-agents), as key innovations in intelligent software engineering, are poised in the industry's end-of-programming debate to transcend from assis...

arxiv 📄 Generating Move Smart Contracts based on Concepts http://arxiv.org/abs/2412.12513v1 The growing adoption of formal verification for smart contracts has spurred the development of new verifiable languages like Move. However, the limited availability of training data for these languages h...

arxiv 📄 PromptV: Leveraging LLM-powered Multi-Agent Prompting for High-quality Verilog Generation http://arxiv.org/abs/2412.11014v1 Recent advances in agentic LLMs have demonstrated remarkable automated Verilog code generation capabilities. However, existing approaches either demand substanti...

Applications for our GenAI faculty position in the CSE department at UCSC close on Friday. Come and join our amazing team in Silicon Valley > recruit.ucsc.edu/JPF01825 Ensure your applications are submitted by Friday as they will be reviewed over the Holiday Break!

arxiv 📄 DialogAgent: An Auto-engagement Agent for Code Question Answering Data Production http://arxiv.org/abs/2412.08069v1 Large Language Models (LLMs) have become increasingly integral to enhancing developer productivity, particularly in code generation, comprehension, and repair tasks. How...

arxiv 📄 Automated Soap Opera Testing Directed by LLMs and Scenario Knowledge: Feasibility, Challenges, and Road Ahead http://arxiv.org/abs/2412.08581v1 Exploratory testing (ET) harnesses tester's knowledge, creativity, and experience to create varying tests that uncover unexpected bugs from t...

arxiv 📄 You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects http://arxiv.org/abs/2412.10133v1 The ability to execute the test suite of a project is essential in many scenarios, e.g., to assess code quality and code coverage, to validate code changes made by developers o...

arxiv 📄 MAGE: A Multi-Agent Engine for Automated RTL Code Generation http://arxiv.org/abs/2412.07822v1 The automatic generation of RTL code (e.g., Verilog) through natural language instructions has emerged as a promising direction with the advancement of large language models (LLMs). However, p...

arxiv 📄 AiEDA: Agentic AI Design Framework for Digital ASIC System Design http://arxiv.org/abs/2412.09745v1 The paper addresses advancements in Generative Artificial Intelligence (GenAI) and digital chip design, highlighting the integration of Large Language Models (LLMs) in automating hardware...

arxiv 📄 ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration http://arxiv.org/abs/2412.05366v1 Through training on publicly available source code libraries, large language models (LLMs) can invoke multiple encapsulated APIs to solve complex pro...

arxiv 📄 The BrowserGym Ecosystem for Web Agent Research http://arxiv.org/abs/2412.05467v1 The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those leveraging automation and Large Language Models (LLMs) for web interaction ta...

arxiv 📄 GEE-OPs: An Operator Knowledge Base for Geospatial Code Generation on the Google Earth Engine Platform Powered by Large Language Models http://arxiv.org/abs/2412.05587v1 As the scale and complexity of spatiotemporal data continue to grow rapidly, the use of geospatial modeling on the ...

arxiv 📄 Applications and Implications of Large Language Models in Qualitative Analysis: A New Frontier for Empirical Software Engineering http://arxiv.org/abs/2412.06564v1 The use of large language models (LLMs) for qualitative analysis is gaining attention in various fields, including softwa...

arxiv 📄 Examining the Use and Impact of an AI Code Assistant on Developer Productivity and Experience in the Enterprise http://arxiv.org/abs/2412.06603v1 AI assistants are being created to help software engineers conduct a variety of coding-related tasks, such as writing, documenting, and tes...

arxiv 📄 Why Do Developers Engage with ChatGPT in Issue-Tracker? Investigating Usage and Reliance on ChatGPT-Generated Code http://arxiv.org/abs/2412.06757v1 Large language models (LLMs) like ChatGPT have shown the potential to assist developers with coding and debugging tasks. However, their ...

arxiv 📄 DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent http://arxiv.org/abs/2412.05311v1 In the advanced technology nodes, the integrated design rule checker (DRC) is often utilized in place and route tools for fast optimization loops for power-performance-area. I...

arxiv 📄 HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design http://arxiv.org/abs/2412.05393v1 With Large Language Models (LLMs) recently demonstrating impressive proficiency in code generation, it is promising to extend their abilities to Hardware Description Languag...

arxiv 📄 Specification-Driven Code Translation Powered by Large Language Models: How Far Are We? http://arxiv.org/abs/2412.04590v1 Large Language Models (LLMs) are increasingly being applied across various domains, including code-related tasks such as code translation. Previous studies have ex...

arxiv 📄 EDA-Aware RTL Generation with Large Language Models http://arxiv.org/abs/2412.04485v1 Large Language Models (LLMs) have become increasingly popular for generating RTL code. However, producing error-free RTL code in a zero-shot setting remains highly challenging for even state-of-the-art...

arxiv 📄 Generating Critical Scenarios for Testing Automated Driving Systems http://arxiv.org/abs/2412.02574v1 Autonomous vehicles (AVs) have demonstrated significant potential in revolutionizing transportation, yet ensuring their safety and reliability remains a critical challenge, especially w...

arxiv 📄 CPP-UT-Bench: Can LLMs Write Complex Unit Tests in C++? http://arxiv.org/abs/2412.02735v1 We introduce CPP-UT-Bench, a benchmark dataset to measure C++ unit test generation capability of a large language model (LLM). CPP-UT-Bench aims to reflect a broad and diverse set of C++ codebases ...

arxiv 📄 TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved? http://arxiv.org/abs/2412.02883v1 Test-driven development (TDD) is the practice of writing tests first and coding later, and the proponents of TDD expound its numerous benefits. For instance, given an iss...

arxiv 📄 Does Few-Shot Learning Help LLM Performance in Code Synthesis? http://arxiv.org/abs/2412.02906v1 Large language models (LLMs) have made significant strides at code generation through improved model design, training, and chain-of-thought. However, prompt-level optimizations remain an imp...

arxiv 📄 System Test Case Design from Requirements Specifications: Insights and Challenges of Using ChatGPT http://arxiv.org/abs/2412.03693v1 System testing is essential in any software development project to ensure that the final products meet the requirements. Creating comprehensive test cas...

arxiv 📄 Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair http://arxiv.org/abs/2412.03905v1 LLMs have garnered considerable attention for their potential to streamline Automated Program Repair (APR). LLM-based approaches can either insert the corr...

arxiv 📄 Large Language Model (LLM) for Standard Cell Layout Design Optimization http://arxiv.org/abs/2406.06549v1 Standard cells are essential components of modern digital circuit designs. With process technologies advancing toward 2nm, more routability issues have arisen due to the decreasing ...

arxiv 📄 RTL-Repo: A Benchmark for Evaluating LLMs on Large-Scale RTL Design Projects http://arxiv.org/abs/2405.17378v1 Large Language Models (LLMs) have demonstrated potential in assisting with Register Transfer Level (RTL) design tasks. Nevertheless, there remains to be a significant gap in ...

arxiv 📄 Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving http://arxiv.org/abs/2407.00079v3 Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates the prefill and deco...

arxiv 📄 LLM-Aided Testbench Generation and Bug Detection for Finite-State Machines http://arxiv.org/abs/2406.17132v1 This work investigates the potential of tailoring Large Language Models (LLMs), specifically GPT3.5 and GPT4, for the domain of chip testing. A key aspect of chip design is fun...

arxiv 📄 MG-Verilog: Multi-grained Dataset Towards Enhanced LLM-assisted Verilog Generation http://arxiv.org/abs/2407.01910v2 Large Language Models (LLMs) have recently shown promise in streamlining hardware design processes by encapsulating vast amounts of domain-specific data. In addition, t...

arxiv 📄 Classification-Based Automatic HDL Code Generation Using LLMs http://arxiv.org/abs/2407.18326v1 While large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits, they still suffer from the hallucination problem, w...

arxiv 📄 Large Language Model for Verilog Generation with Golden Code Feedback http://arxiv.org/abs/2407.18271v2 Recent advancements in large language models (LLMs) have catalyzed significant interest in the automatic generation of Register-Transfer Level (RTL) code, particularly Verilog, from n...

arxiv 📄 AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs http://arxiv.org/abs/2407.18333v1 Recently, the use of large language models (LLMs) for software code generation, e.g., C/C++ and Python, has proven a great success. However, LLMs still suffer from low...

arxiv 📄 OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection http://arxiv.org/abs/2407.16237v2 Recent studies have demonstrated the significant potential of Large Language Models (LLMs) in generating Register Transfer Level (RTL) code, with notable advanceme...

arxiv 📄 Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design http://arxiv.org/abs/2407.18276v3 Large Language Models (LLMs) are effective in computer hardware synthesis via hardware description language (HDL) generation. However, LLM-assisted approaches for HD...

arxiv 📄 Interactive and Automatic Generation of Primitive Custom Circuit Layout Using LLMs http://arxiv.org/abs/2408.07279v1 In this study, we investigate the use of Large Language Models (LLMs) for the interactive and automated production of customs circuit layouts described in natural langu...

arxiv 📄 Evaluating Large Language Models for Automatic Register Transfer Logic Generation via High-Level Synthesis http://arxiv.org/abs/2408.02793v1 The ever-growing popularity of large language models (LLMs) has resulted in their increasing adoption for hardware design and verification. Prio...

arxiv 📄 LAAG-RV: LLM Assisted Assertion Generation for RTL Design Verification http://arxiv.org/abs/2409.15281v1 Writing SystemVerilog Assertions (SVA) is an important but complex step in verifying Register Transfer Level (RTL) designs. Conventionally, experts need to understand the design spec...

arxiv 📄 Are LLMs Any Good for High-Level Synthesis? http://arxiv.org/abs/2408.10428v1 The increasing complexity and demand for faster, energy-efficient hardware designs necessitate innovative High-Level Synthesis (HLS) methodologies. This paper explores the potential of Large Language Models (L...

arxiv 📄 Revisiting VerilogEval: Newer LLMs, In-Context Learning, and Specification-to-RTL Tasks http://arxiv.org/abs/2408.11053v1 The application of large-language models (LLMs) to digital hardware code generation is an emerging field. Most LLMs are primarily trained on natural language and s...