Related papers: BUILD-AND-FIND: An Effort-Aware Protocol for Evalu…
In this paper we present attestable builds, a new paradigm to provide strong source-to-binary correspondence in software artifacts. We tackle the challenge of opaque build pipelines that disconnect the trust between source code, which can…
Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evaluate code agents in such authentic, workflow-driven scenarios.…
Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and…
Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not…
Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development. As intelligent completion tools evolve, we need a robust evaluation…
Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to only generate frontend web pages, masking the lack of real full-stack data…
In conversational search systems, a key component is to determine and clarify the intent behind complex queries. We view intent clarification in light of the exploratory search paradigm, where users, through an iterative, evolving process…
This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property. We define agentic systems as goal-directed, tool-using decision makers operating in closed loops, and show how reliability emerges…
To evaluate software maintenance techniques and tools in controlled experiments with human participants, researchers currently use projects and tasks selected on an ad-hoc basis. This can unrealistically favor their tool, and it makes the…
Foundation model-enabled generative artificial intelligence facilitates the development and implementation of agents, which can leverage distinguished reasoning and language processing capabilities to takes a proactive, autonomous role to…
Structured-workflow agents driven by large language models execute tool calls against sensitive external environments. We propose \codename, a telemetry-driven behavioral anomaly detection firewall. Drawing on sequence-based intrusion…
Decompilation -- recovering source code from compiled binaries -- is essential for security analysis, malware reverse engineering, and legacy software maintenance. However, existing decompilers produce code that often fails to compile or…
We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs. LLM-generated proofs are notoriously correct-but-verbose and brittle across…
Coding agents can generate web applications from natural-language descriptions, yet a recent benchmark study shows that generated applications fail to meet functional requirements in over 70% of cases. The core difficulty is that web…
Process discovery is one of the primary process mining tasks and starting point for process improvements using event data. Existing process discovery techniques aim to find process models that best describe the observed behavior. The focus…
Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding to physical AI. A core requirement in these settings is the ability to both explore the problem space and exploit acquired…
Agentic coding tools, such as OpenAI Codex, Claude Code, and Cursor, are transforming the software engineering landscape. These AI-powered systems function as autonomous teammates capable of planning and executing complex development tasks.…
Retrieval systems often fail when user queries differ stylistically or semantically from the language used in domain documents. Query rewriting has been proposed to bridge this gap, improving retrieval by reformulating user queries into…
Refactoring is a well-known technique that is widely adopted by software engineers to improve the design and enable the evolution of a system. Knowing which refactoring operations were applied in a code change is a valuable information to…
Scientific algorithm discovery is iterative: hypotheses are proposed, implemented, stress-tested, and revised. Current LLM-guided search systems accelerate proposal generation, but often under-represent scientific structure by optimizing…