Related papers: SIA: Self Improving AI with Harness & Weight Updat…

Self-improving agents aim to continuously acquire new capabilities with minimal supervision. However, current approaches face two key limitations: their self-improvement processes are often rigid, fail to generalize across tasks domains,…

Central to human-aligned AI is understanding the benefits of human-elicited labels over synthetic alternatives. While human soft-labels improve calibration by capturing uncertainty, prior studies conflate these benefits with the implicit…

Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as…

Agent harness evolution improves frozen language-model agents by modifying the executable structures around them. We study this paradigm as a form of sample-efficient fast adaptation: instead of updating model weights, an agent can acquire…

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from…

Machine Learning algorithms have been extensively researched throughout the last decade, leading to unprecedented advances in a broad range of applications, such as image classification and reconstruction, object recognition, and text…

Multi-agent AI systems powered by large language models (LLMs) are increasingly applied to solve complex tasks. However, these systems often rely on fragile, manually designed prompts and heuristics, making optimization difficult. A key…

Bias in AI systems, especially those relying on natural language data, raises ethical and practical concerns. Underrepresentation of certain groups often leads to uneven performance across demographics. Traditional fairness methods, such as…

We present CAIA, a benchmark exposing a critical blind spot in AI evaluation: the inability of state-of-the-art models to operate in adversarial, high-stakes environments where misinformation is weaponized and errors are irreversible. While…

Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's \emph{workspace}, the structured external substrate it reads, writes, and tests; we call its…

To survive and thrive in complex environments, humans have evolved sophisticated self-improvement mechanisms through environment exploration, hierarchical abstraction of experiences into reuseable skills, and collaborative construction of…

Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrained context windows and static policies that fail to adapt to dynamic environments. To address these limitations, this work proposes the…

Timely and high-quality feedback is essential for effective learning in programming courses; yet, providing such support at scale remains a challenge. While AI-based systems offer scalable and immediate help, their responses can…

Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by…

Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components…

This paper documents a case study in agent-driven autonomous reinforcement learning research for quadruped locomotion. The setting was not a fully self-starting research system. A human provided high-level directives through an agentic…

This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The performance of agent systems built on LLMs…

AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires…

Spatial disorientation is a leading cause of fatal aircraft accidents. This paper explores the potential of AI agents to aid pilots in maintaining balance and preventing unrecoverable losses of control by offering cues and corrective…