Related papers: Agentic Metacognition: Designing a "Self-Aware" Lo…
Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven…
The possibility of LLM self-awareness and even sentience is gaining increasing public attention and has major safety and policy implications, but the science of measuring them is still in a nascent state. Here we introduce a novel…
Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the software industry to automate complex engineering tasks. However, these agents are prone to a wide range of misbehaviors, such as…
Agent-assisted memory recall is one critical research problem in the field of human-computer interaction. In conventional methods, the agent can retrieve information from its equipped memory module to help the person recall incomplete or…
When deployed, AI agents will encounter problems that are beyond their autonomous problem-solving capabilities. Leveraging human assistance can help agents overcome their inherent limitations and robustly cope with unfamiliar situations. We…
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…
Mobile agentic AI is extending autonomous capabilities to resource-constrained platforms such as edge robots and unmanned aerial vehicles (UAVs), where strict size, weight, power, and cost (SWAP-C) constraints and intermittent wireless…
Reactions such as gestures, facial expressions, and vocalizations are an abundant, naturally occurring channel of information that humans provide during interactions. A robot or other agent could leverage an understanding of such implicit…
Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…
As data continues to grow in scale and complexity, preparing, transforming, and analyzing it remains labor-intensive, repetitive, and difficult to scale. Since data contains knowledge and AI learns knowledge from it, the alignment between…
Large language model-based agents are increasingly being integrated into core battlefield functions, including intelligence analysis, data fusion, and battlefield management. This paper argues that the very features that make such agents…
Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…
People navigate complex environments using cues, heuristics, and other strategies, which are often adaptive in stable settings. However, as AI increasingly permeates society's information environments, those become more adaptive and…
With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to…
Autonomous agents are increasingly entrusted with complex, long-horizon tasks, ranging from mathematical reasoning to software generation. While agentic workflows facilitate these tasks by decomposing them into multi-step reasoning chains,…
In humans, perceptual awareness facilitates the fast recognition and extraction of information from sensory input. This awareness largely depends on how the human agent interacts with the environment. In this work, we propose active neural…
Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environments. Yet, in conversational benchmarks, which simulate real-world customer-centric issue…
In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations. In this manuscript we focus on predictions expressed as General Value Functions:…
Eliciting reasoning has emerged as a powerful technique for improving the performance of large language models (LLMs) on complex tasks by inducing thinking. However, their effectiveness in realistic user-engaged agent scenarios remains…
Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…