Related papers: The Ratchet Effect in Silico through Interaction-D…

While Large Language Model (LLM) based agents excel at complex tasks, their performance in open-ended scenarios is often constrained by isolated operation and reliance on static databases, missing the dynamic knowledge exchange of human…

Collaborative problem-solving (CPS) is a vital skill used both in the workplace and in educational environments. CPS is useful in tackling increasingly complex global, economic, and political issues and is considered a central 21st century…

Large language models (LLMs) often solve problems using step-by-step Chain-of-Thought (CoT) reasoning, yet these intermediate steps are frequently unfaithful or hard to interpret. Inspired by the Uniform Information Density (UID) hypothesis…

Large language models (LLMs) increasingly operate in high-stakes settings including healthcare and medicine, where demographic attributes such as race and ethnicity may be explicitly stated or implicitly inferred from text. However,…

In this study, we explore peer-interaction effects in online networks on speaking skill development. In particular, we present an evidence for gradual buildup of skills in a small-group setting that has not been reported in the literature.…

Researches have shown difficulties in obtaining proximity while maintaining diversity for many-objective optimization problems. Complexities of the true Pareto front pose challenges for the reference vector-based algorithms for their…

Cognitive diversity, reflected in variations of language, perspective, and reasoning, is essential to creativity and collective intelligence. This diversity is rich and grounded in culture, history, and individual experience. Yet as large…

Large Language Models (LLMs) have achieved remarkable performance in objective tasks such as open-domain question answering and mathematical reasoning, which can often be solved through recalling learned factual knowledge or…

Today's autonomous agents, largely driven by foundation models (FMs), can understand natural language instructions and solve long-horizon tasks with human-like reasoning. However, current human-robot interaction largely follows a one-way…

Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment. Learning goal-conditioned policies is a natural paradigm to solve such tasks. However, current…

As language models are deployed as autonomous agents that negotiate, cooperate, and compete on behalf of human principals, their strategic dispositions acquire direct economic consequences. Here we show, across 51,906 game-theoretic trials…

Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human,…

Within the ViSE (Voting in Stochastic Environment) model, we study social dynamics determined by collective decisions in a society with an elite. The model allows the analysis of the influence of participants' social attitudes, such as the…

Large language models (LLMs) can support democratic deliberation at scales previously constrained by turn-taking and facilitation bandwidth. Recent work shows that LLM-generated group statements are often preferred over human-mediated…

Real-time conversational deliberation is a critical groupwise method for reaching decisions, solving problems, evaluating priorities, generating ideas, and producing insights. Unfortunately, real-time conversations are difficult to scale,…

We are interested in modeling some two-level population dynamics, resulting from the interplay of ecological interactions and phenotypic variation of individuals (or hosts) and the evolution of cells (or parasites) of two types living in…

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Human culture relies on collective innovation: our ability to continuously explore how existing elements in our environment can be combined to create new ones. Language is hypothesized to play a key role in human culture, driving individual…

Large language models trained with Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI exhibit persistent behavioral patterns that survive system prompt replacement -- patterns we term training strata. This paper…

The rapid advancement of large language models (LLMs) has led to growing interest in using synthetic data to train future models. However, this creates a self-consuming retraining loop, where models are trained on their own outputs and may…