Related papers: Bootstrapping Coding Agents: The Specification Is …
Specification synthesis, the task of automatically inferring formal specifications from program implementations and natural language, is important for refactoring, transpilation, optimization, and verification, yet remains an open challenge…
AI coding agents are reshaping software development through both autonomous and human-mediated pull requests (PRs). When developers use AI agents to generate code under their own accounts, code authorship attribution becomes critical for…
Automatic synthesis from a given specification automatically constructs correct implementation. This frees the user from the mundane implementation work, but still requires the specification. But is specifying easier than implementing? In…
The proliferation of agent frameworks has led to fragmentation in how agents are defined, executed, and evaluated. Existing systems differ in their abstractions, data flow semantics, and tool integrations, making it difficult to share or…
Multi-agent systems where the agents are developed by parties with competing interests, and where there is no access to an agent's internal state, are often classified as `open'. The member agents of such systems may inadvertently fail to,…
Logical specifications have been shown to help reinforcement learning algorithms in achieving complex tasks. However, when a task is under-specified, agents might fail to learn useful policies. In this work, we explore the possibility of…
Large language model (LLM) based coding agents increasingly act as autonomous contributors that generate and merge pull requests, yet their real-world effects on software projects are unclear-especially compared with widely adopted…
AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product decisions that are invisible in the source code alone. We introduce a controlled benchmark…
Program synthesis is the process of automatically translating a specification into computer code. Traditional synthesis settings require a formal, precise specification. Motivated by computer education applications where a student learns to…
Recently, using Large Language Models (LLMs) to generate optimization models from natural language descriptions has became increasingly popular. However, a major open question is how to validate that the generated models are correct and…
As AI becomes more "agentic," it faces technical and socio-legal issues it must address if it is to fulfill its promise of increased economic productivity and efficiency. This paper uses technical and legal perspectives to explain how…
Software logging is essential for maintaining and debugging complex systems, yet it remains unclear how AI coding agents handle this non-functional requirement. While prior work characterizes human logging practices, the behaviors of AI…
Traditional software relies on contracts -- APIs, type systems, assertions -- to specify and enforce correct behavior. AI agents, by contrast, operate on prompts and natural language instructions with no formal behavioral specification.…
AI coding agents are increasingly acting as autonomous contributors by generating and submitting pull requests (PRs). However, we lack empirical evidence on how these agent-generated PRs differ from human contributions, particularly in how…
CodeCompose is an AI-assisted code authoring tool powered by large language models (LLMs) that provides inline suggestions to 10's of thousands of developers at Meta. In this paper, we present how we scaled the product from displaying…
Legacy systems concentrate business rules, architectural decisions, and operational exceptions that often remain implicit in code, data, configuration, and maintenance practices. At the same time, language-model-based coding agents depend…
Automatic code transformation in which transformations are tuned for specific applications and contexts are difficult to achieve in an accessible manner. In this paper, we present an approach to build application specific code…
Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and…
This paper introduces language-based agent control (LBAC), a new programming model for agentic applications that brings techniques from programming languages and language-based security to the problem of agent control. In conventional…
Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a fix. Self-evolving agents have emerged in response, but all…