相关论文: Interleaving Fast and Slow Decision Making

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Conventional reinforcement learning (RL) allows an agent to learn policies via environmental rewards only, with a long and slow learning curve, especially at the beginning stage. On the contrary, human learning is usually much faster…

This is the first of a series of papers that the authors propose to write on the subject of improving the speed of response of learning systems using multiple models. During the past two decades, the first author has worked on numerous…

This position paper proposes a fundamental shift in designing code generation models: treating reasoning depth as a controllable resource. Rather than being an incidental byproduct of prompting, we argue that the trade-off between rapid,…

The integration of Artificial Intelligence (AI) necessitates determining whether systems function as tools or collaborative teammates. In this study, by synthesizing Human-AI Interaction (HAI) literature, we analyze this distinction across…

By late 20th century, the rationality wars had launched debates about the nature and norms of intuitive and reflective thinking. Those debates drew from mid-20th century ideas such as bounded rationality, which challenged more idealized…

Implicit biases in both humans and large language models (LLMs) pose significant societal risks. Dual process theories propose that biases arise primarily from associative System 1 thinking, while deliberative System 2 thinking mitigates…

Spurious correlations were found to be an important factor explaining model performance in various NLP tasks (e.g., gender or racial artifacts), often considered to be ''shortcuts'' to the actual task. However, humans tend to similarly make…

This paper introduces System 0, a conceptual framework for understanding how artificial intelligence functions as a cognitive extension preceding both intuitive (System 1) and deliberative (System 2) thinking processes. As AI systems…

The Type Indeterminacy model is a theoretical framework that formalizes the constructive preference perspective suggested by Kahneman and Tversky. In this paper we explore an extention of the TI-model from simple to strategic…

Dual process models of cognition suggest there are two kinds of thought: rapid, automatic Type 1 processes, and effortful, controlled Type 2 processes. Models of creative thinking also distinguish between two sets of processes: those…

We consider open multi-agent systems. Unlike the systems usually studied in the literature, here agents may join or leave while the process studied takes place. The system composition and size evolve thus with time. We focus here on systems…

AI agents are increasingly deployed in complex, interactive environments, yet their runtime remains a major bottleneck for training, evaluation, and real-world use. Typical agent behavior unfolds sequentially, with each action requiring an…

Ensuring safe, comfortable, and efficient planning is crucial for autonomous driving systems. While end-to-end models trained on large datasets perform well in standard driving scenarios, they struggle with complex low-frequency events.…

Current large-language models (LLMs) typically adopt a fixed reasoning strategy, either simple or complex, for all questions, regardless of their difficulty. This neglect of variation in task and reasoning process complexity leads to an…

As humans learn new skills and apply their existing knowledge while maintaining previously learned information, "continual learning" in machine learning aims to incorporate new data while retaining and utilizing past knowledge. However,…

This work explores dynamics existing in interactions between players. The dynamic system of games is a new attitude to modeling in which an event is modeled using several games. The model allows us to analyze the interplay capabilities and…

Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) reasoning, they incur…

Reasoning models have attracted increasing attention for their ability to tackle complex tasks, embodying the System II (slow thinking) paradigm in contrast to System I (fast, intuitive responses). Yet a key question remains: Does slower…

We study reinforcement learning in settings where sampling an action from the policy must be done concurrently with the time evolution of the controlled system, such as when a robot must decide on the next action while still performing the…