Related papers: From Runnable to Shippable: Multi-Agent Test-Drive…
While a lot of recent research focuses on enhancing the textual reasoning capabilities of Large Language Models (LLMs) by optimizing the multi-agent framework or reasoning chains, several benchmark tasks can be solved with 100\% success…
The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of random sampling and shallow generation, often yield simple…
Developing 3D games requires specialized expertise across multiple domains, including programming, 3D modeling, and engine configuration, which limits access to millions of potential creators. Recently, researchers have begun to explore…
In recent years, AI-based software engineering has progressed from pre-trained models to advanced agentic workflows, with Software Development Agents representing the next major leap. These agents, capable of reasoning, planning, and…
Mobile applications play an important role in the economy today and there is an increasing trend for app enablement on multiple platforms. However, creating, distributing, and maintaining an application remain expert tasks. Even for…
We study the problem of designing AI agents that can robustly cooperate with people in human-machine partnerships. Our work is inspired by real-life scenarios in which an AI agent, e.g., a virtual assistant, has to cooperate with new users…
Large Language Models (LLMs) have shown incredible potential in code generation tasks, and recent research in prompt engineering have enhanced LLMs' understanding of textual information. However, ensuring the accuracy of generated code…
Computer-aided design (CAD) is fundamental to modern engineering and manufacturing, but creating CAD models still requires expert knowledge and specialized software. Recent advances in large language models (LLMs) open up the possibility of…
Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment. We define this paradigm as Test-Time Improvement (TTI). However, the mechanisms under how and why…
Dependent types help programmers write highly reliable code. However, this reliability comes at a cost: it can be challenging to write new prototypes in (or migrate old code to) dependently-typed programming languages. Gradual typing makes…
To adequately test modern code generation systems, evaluation benchmarks must execute and test the code generated by the system. However, these execution and testing requirements have largely limited benchmarks to settings where code is…
Multi-agent frameworks promise to simplify LLM-driven software development, yet there is no principled way to evaluate their developer experience in a controlled setting. We introduce DDL2PropBank, a novel benchmark task that maps…
A great part of software development involves conceptualizing or communicating the underlying procedures and logic that needs to be expressed in programs. One major difficulty of programming is turning concept into code, especially when…
Context: Technical Debt requirements are related to the distance between the ideal value of the specification and the system's actual implementation, which are consequences of strategic decisions for immediate gains, or unintended changes…
Multi-agent systems, where multiple agents (generative AI models + tools) collaborate, are emerging as an effective pattern for solving long-running, complex tasks in numerous domains. However, specifying their parameters (such as models,…
With the continued scaling of advanced technology nodes, the design-technology co-optimization (DTCO) paradigm has become increasingly critical, rendering efficient device design and optimization essential. In the domain of TCAD simulation,…
Automated code generation driven by Large Lan- guage Models (LLMs) has enhanced development efficiency, yet generating complex application-level software code remains challenging. Multi-agent frameworks show potential, but existing methods…
The core challenge in automotive exterior design is balancing subjective aesthetics with objective aerodynamic performance while dramatically accelerating the development cycle. To address this, we propose a novel, LLM-driven multi-agent…
While programming is one of the most broadly applicable skills in modern society, modern machine learning models still cannot code solutions to basic problems. Despite its importance, there has been surprisingly little work on evaluating…
Generating code from a natural language using Large Language Models (LLMs) such as ChatGPT, seems groundbreaking. Yet, with more extensive use, it's evident that this approach has its own limitations. The inherent ambiguity of natural…