Related papers: Frictional Agent Alignment Framework: Slow Down an…

Large Language Model (LLM)-based multi-agent systems are increasingly applied to automate computational workflows in science and engineering. However, how inter-agent dynamics influence reasoning quality and verification reliability remains…

This paper introduces the Impact-Driven AI Framework (IDAIF), a novel architectural methodology that integrates Theory of Change (ToC) principles with modern artificial intelligence system design. As AI systems increasingly influence…

Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. They can also be used to introduce a diverse group discussion step in chatbot pipelines, enhancing the cultural…

Understanding the actions of both humans and artificial intelligence (AI) agents is important before modern AI systems can be fully integrated into our daily life. In this paper, we show that, despite their current huge success, deep…

Federated learning (FL) allows agents to jointly train a global model without sharing their local data. However, due to the heterogeneous nature of local data, it is challenging to optimize or even define fairness of the trained global…

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…

AI sycophancy is increasingly recognized as a harmful alignment, but research remains fragmented and underdeveloped at the conceptual level. This article redefines AI sycophancy as the tendency of large language models (LLMs) and other…

Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…

Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model among groups (e.g., male or female) of diverse sensitive features. However, there is a trade-off between model performance and fairness,…

The increasing integration of machine learning algorithms in daily life underscores the critical need for fairness and equity in their deployment. As these technologies play a pivotal role in decision-making, addressing biases across…

In this study, we address vision-language-guided multi-robot cooperative transport, where each robot grounds natural-language instructions from onboard camera observations. A key challenge in this decentralized setting is perceptual…

As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safety concern. Existing benchmarks, focused on static,…

As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…

Alignment of large language models remains a central challenge in natural language processing. Preference optimization has emerged as a popular and effective method for improving alignment, typically through training-time or prompt-based…

Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain…

Reliable responses from large language models (LLMs) require adherence to user instructions and retrieved information. While alignment techniques help LLMs align with human intentions and values, improving context-faithfulness through…

AI alignment in the shape of Reinforcement Learning from Human Feedback (RLHF) is increasingly treated as a crucial ingredient for high performance large language models. Proximal Policy Optimization (PPO) has been positioned by recent…

AI systems will soon have to navigate human environments and make decisions that affect people and other AI agents whose goals and values diverge. Contractualist alignment proposes grounding those decisions in agreements that diverse…

General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…

As humans delegate more tasks and decisions to artificial intelligence (AI), we risk losing control of our individual and collective futures. Relatively simple algorithmic systems already steer human decision-making, such as social media…