Related papers: BUILD-AND-FIND: An Effort-Aware Protocol for Evalu…

Ad hoc dataset search requires matching underspecified natural-language queries against sparse, heterogeneous metadata records, a task where typical lexical or dense retrieval alone falls short. We reposition dataset search as a…

Collaborative tasks are ubiquitous activities where a form of communication is required in order to reach a joint goal. Collaborative building is one of such tasks. We wish to develop an intelligent builder agent in a simulated building…

Requirements traceability in safety-critical software development remains largely dependent on external documentation maintained separately from the systems it describes. This separation introduces structural fragility: traces degrade…

We study cost-efficient collaboration between strong and weak language models for repository-level code generation, where the weak model handles simpler tasks at lower cost, and the most challenging tasks are delegated to the strong model.…

Discovering a solution in a combinatorial space is prevalent in many real-world problems but it is also challenging due to diverse complex constraints and the vast number of possible combinations. To address such a problem, we introduce a…

AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of…

Code assistants are increasingly utilized in test-driven software development, yet the theoretical mechanisms behind their environment-interaction strategies remain underexplored. We provide a probabilistic framework for two dominant…

In bridge inspection, engineers should diagnose the observed bridge defects by identifying the factors underlying those defects. Traditionally, engineers search and organize structural condition-related information based on visual…

Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how…

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…

Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge. Existing benchmarks face a…

Computer-aided design (CAD) is the backbone of modern industrial design, yet learned CAD generators still fall short of real engineering pipelines: they neither iterate like engineers nor evaluate what engineering requires. Prior work has…

AI systems are becoming active participants in organizational and knowledge work. They increasingly interact with humans, coordinate workflows, and operate in multi-agent arrangements. Understanding their effects therefore requires more…

Building trust in reinforcement learning (RL) agents requires understanding why they make certain decisions, especially in high-stakes applications like robotics, healthcare, and finance. Existing explainability methods often focus on…

While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal…

Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assessment. This leaves out a basic question: can an agent keep its own codebase working as…

Large Language Models (LLMs) have made significant strides in code generation and problem solving. Current approaches employ external tool-based iterative debuggers that use compiler or other tool-based runtime feedback to refine coarse…

Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, the design and…

Software Repositories contain knowledge on how software engineering teams work, communicate, and collaborate. It can be used to develop a data-informed view of a team's development process, which in turn can be employed for process…

AI coding agents are increasingly integrated into real-world software development workflows, yet their robustness under diverse and adversarial scenarios remains poorly understood. We present ABTest, a behavior-driven fuzzing framework that…