Related papers: Soft-Label Governance for Distributional Safety in…

We propose the use of Agent Based Models (ABMs) inside a reinforcement learning framework in order to better understand the relationship between automated decision making tools, fairness-inspired statistical constraints, and the social…

This article introduces a decentralized robust optimization framework for safe multi-agent control under uncertainty. Although stochastic noise has been the primary form of modeling uncertainty in such systems, these formulations might fall…

As the social environment is growing more complex and collaboration is deepening, factors affecting the healthy development of service ecosystem are constantly changing and diverse, making its governance a crucial research issue. Applying…

Distributed scientific workflows increasingly span heterogeneous compute clusters, edge resources, and geo-distributed data repositories. In these environments, a centralized orchestrator is an architectural bottleneck -- introducing a…

Large language models (LLMs) are increasingly deployed in high-stakes domains, where rare but severe failures can result in irreversible harm. However, prevailing evaluation benchmarks often reduce complex social risk to mean-centered…

Contemporary approaches to agent-based modeling (ABM) of social systems have traditionally emphasized rule-based behaviors, limiting their ability to capture nuanced dynamics by moving beyond predefined rules and leveraging contextual…

Deploying large language model (LLM) agents in shared environments introduces a fundamental tension between individual alignment and collective stability: locally rational decisions can impose negative externalities that degrade…

Large language model agents suffer from fundamental architectural problems: entangled reasoning and execution, memory volatility, and uncontrolled action sequences. We introduce Structured Cognitive Loop (SCL), a modular architecture that…

Large language models are increasingly proposed as autonomous agents for high-stakes public workflows, yet we lack systematic evidence about whether they would follow institutional rules when granted authority. We present evidence that…

Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in…

Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation, yet they suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value…

As AI systems evolve into distributed ecosystems with autonomous execution, asynchronous reasoning, and multi-agent coordination, the absence of scalable, decoupled governance poses a structural risk. Existing oversight mechanisms are…

As reinforcement learning agents become increasingly integrated into complex, real-world environments, designing for safety becomes a critical consideration. We specifically focus on researching scenarios where agents can cause undesired…

The proliferation of harmful memes on online media poses significant risks to public health and stability. Existing detection methods heavily rely on large-scale labeled data for training, which necessitates substantial manual annotation…

A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these considerations change as we move…

Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision…

As AI systems pervade human life, ensuring that large language models (LLMs) make safe decisions remains a significant challenge. We introduce the Governance of the Commons Simulation (GovSim), a generative simulation platform designed to…

Reinsurance decision-making exhibits the core structural properties that motivate multi-agent models: distributed and asymmetric information, partial observability, heterogeneous epistemic responsibilities, simulator-driven environment…

Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversational functions and maintain safety in behavioral health communication. We propose a safety-aware, role-orchestrated multi-agent LLM…

In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…