Related papers: When Agents Disagree With Themselves: Measuring Be…

Large Language Models (LLMs) have demonstrated remarkable success in conversational systems by generating human-like responses. However, they can fall short, especially when required to account for personalization or specific knowledge. In…

Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software requires strict adherence to structural constraints, such as architectural…

Over these years, multi-agent reinforcement learning has achieved remarkable performance in multi-agent planning and scheduling tasks. It typically follows the self-play setting, where agents are trained by playing with a fixed group of…

Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting produces meaningful and reproducible behavioral diversity. We investigate whether…

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…

We propose a novel in-context learning algorithm for building autonomous decision-making language agents. The language agent continuously attempts to solve the same task by self-correcting each time the task fails. Our selected language…

Effective modeling of how human travelers learn and adjust their travel behavior from interacting with transportation systems is critical for system assessment and planning. However, this task is also difficult due to the complex cognition…

We establish empirical bounds on behavioral inference through controlled experiments at scale: LLM-based agents assigned one of 36 behavioral profiles (9 belief systems x 4 motivations) generate over 1.5 million behavioral sequences across…

Multi-agent LLM committees replicate the same model under different role prompts and aggregate outputs by majority vote, implicitly assuming that agents contribute complementary evidence. We embed each agent's chain-of-thought rationale and…

This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging $U$-statistics for output-level…

Modern LLM agents solve complex tasks by operating in iterative execution loops, where they repeatedly reason, act, and self-evaluate progress to determine when a task is complete. In this work, we show that while this self-directed loop…

Effective asynchronous planning, or the ability to efficiently reason and plan over states and actions that must happen in parallel or sequentially, is essential for agents that must account for time delays, reason over diverse long-horizon…

Based on their superior comprehension and reasoning capabilities, Large Language Model (LLM) driven agent frameworks have achieved significant success in numerous complex reasoning tasks. ReAct-like agents can solve various intricate…

In this work, we report what happens when two large language models respond to each other for many turns without any outside input in a multi-agent setup. The setup begins with a short seed sentence. After that, each model reads the other's…

Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of training data. Large language models (LLMs) have recently…

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…

This paper presents a learning framework to estimate an agent capability and task requirement model for multi-agent task allocation. With a set of team configurations and the corresponding task performances as the training data, linear task…

Numerous methods have been proposed to measure LLM misgendering, including probability-based evaluations (e.g., automatically with templatic sentences) and generation-based evaluations (e.g., with automatic heuristics or human validation).…

Agency, the capacity to proactively shape events, is central to how humans interact and collaborate. While LLMs are being developed to simulate human behavior and serve as human-like agents, little attention has been given to the Agency…

AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation…