Related papers: Understanding Persuasion in Long-Running Agents
The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate…
As AI becomes more prevalent throughout society, effective methods of integrating humans and AI systems that leverage their respective strengths and mitigate risk have become an important priority. In this paper, we introduce the paradigm…
Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human…
Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust. To address this, we propose an interactive agent that produces explanations through an auditable sequence of actions. The…
As large language models (LLMs) achieve advanced persuasive capabilities, concerns about their potential risks have grown. The EU AI Act prohibits AI systems that use manipulative or deceptive techniques to undermine informed…
In diffusion social learning over weakly-connected graphs, it has been shown recently that influential agents shape the beliefs of non-influential agents. This paper analyzes this mechanism more closely and addresses two main questions.…
When AI systems summarize and relay information, they inevitably transform it. But how? We introduce an experimental paradigm based on the telephone game to study what happens when AI talks to AI. Across five studies tracking content…
Agentic AI assistants that autonomously perform multi-step tasks raise open questions for user experience: how should such systems communicate progress and reasoning during extended operations, especially in attention-critical contexts such…
Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire…
As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution…
In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…
Smart assistants increasingly act proactively, yet mistimed or intrusive behavior often causes users to lose trust and disable these features. Learning user preferences for proactive assistance is difficult because real-world studies are…
The field of AI is undergoing a fundamental transition from generative models that can produce synthetic content to artificial agents that can plan and execute complex tasks with only limited human involvement. Companies that pioneered the…
This paper shows how agents' choice in communicative action can be designed to mitigate the effect of their resource limits in the context of particular features of a collaborative planning task. I first motivate a number of hypotheses…
As AI becomes more "agentic," it faces technical and socio-legal issues it must address if it is to fulfill its promise of increased economic productivity and efficiency. This paper uses technical and legal perspectives to explain how…
As large language model (LLM)-based agents become increasingly integrated into daily digital interactions, their ability to reason across long interaction histories becomes crucial for providing personalized and contextually aware…
We present Ask WhAI, a systems-level framework for inspecting and perturbing belief states in multi-agent interactions. The framework records and replays agent interactions, supports out-of-band queries into each agent's beliefs and…
To enable effective human-AI collaboration, merely optimizing AI performance without considering human factors is insufficient. Recent research has shown that designing AI agents that take human behavior into account leads to improved…
Recent advances in large language models (LLMs) have enabled the development of AI agents that exhibit increasingly human-like behaviors, including planning, adaptation, and social dynamics across diverse, interactive, and open-ended…
Agentic workflows -- where multiple large language model (LLM) instances interact to solve tasks -- are increasingly built on feedback mechanisms, where one model evaluates and critiques another. Despite the promise of feedback-driven…