Related papers: How Coding Agents Fail Their Users: A Large-Scale …
Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs…
User models in information retrieval rest on a foundational assumption that observed behavior reveals intent. This assumption collapses when the user is an AI agent privately configured by a human operator. For any action an agent takes, a…
Code review is a critical software engineering practice where developers review code changes before integration to ensure code quality, detect defects, and improve maintainability. In recent years, AI agents that can understand code…
The rise of AI agents is transforming how software can be built. The promise of agents is that developers might write code quicker, delegate multiple tasks to different agents, and even write a full piece of software purely out of natural…
Agentic workflows built on low-code orchestration platforms enable rapid development of multi-agent systems, but they also introduce new and poorly understood failure modes that hinder reliability and maintainability. Unlike traditional…
The rapid adoption of AI coding agents and AI assistant web services is fundamentally changing how developers discover, consume, and interact with technical documentation. This paper studies that transformation across three interconnected…
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…
Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here…
The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive…
Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…
Our ability to build autonomous agents that leverage Generative AI continues to increase by the day. As builders and users of such agents it is unclear what parameters we need to align on before the agents start performing tasks on our…
Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called…
AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…
Software developers balance a variety of different tasks in a workweek, yet the allocation of time often differs from what they consider ideal. Identifying and addressing these deviations is crucial for organizations aiming to enhance the…
LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents…
The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks…
AI agents are continually optimized for tasks related to human work, such as software engineering and professional writing, signaling a pressing trend with significant impacts on the human workforce. However, these agent developments have…
General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…
Many studies have long investigated how developers debug, shaping our understanding of debugging and helping motivate the creation of more effective tools. However, less is known about the typical progression of debugging in real world…
Agentic AI workflows (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low. A promising solution is inference-time alignment, which uses extra compute at test time to…