Related papers: Thought Cloning: Learning to Think while Acting by…

AI Agents rely on Large Language Models (LLMs) and Multimodal-LLMs (MLLMs) to perform interpretation and inference in text and image tasks without post-training, where LLMs and MLLMs play the most critical role and determine the initial…

Biological agents learn and act intelligently in spite of a highly limited capacity to process and store information. Many real-world problems involve continuous control, which represents a difficult task for artificial intelligence agents.…

When interacting with people, AI agents do not just influence the state of the world -- they also influence the actions people take in response to the agent, and even their underlying intentions and strategies. Accounting for and leveraging…

Early artificial intelligence paradigms exhibited separated cognitive functions: Neural Networks focused on "perception-representation," Reinforcement Learning on "decision-making-behavior," and Symbolic AI on "knowledge-reasoning." With…

Humans often learn how to perform tasks via imitation: they observe others perform a task, and then very quickly infer the appropriate actions to take based on their observations. While extending this paradigm to autonomous agents is a…

Despite rapid advancements in large language models (LLMs), the token-level autoregressive nature constrains their complex reasoning capabilities. To enhance LLM reasoning, inference-time techniques, including…

How can we build AI systems that can learn any set of individual human values both quickly and safely, avoiding causing harm or violating societal standards for acceptable behavior during the learning process? We explore the effects of…

This paper addresses the general problem of reinforcement learning (RL) in partially observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned from scratch to drive simulated cars from high-dimensional video…

A key objective in artificial intelligence (AI) development is to create systems that match or surpass human creativity. Although current AI models perform well across diverse creative tasks, it remains unclear whether these achievements…

The maturation of cognition, from introspection to understanding others, has long been a hallmark of human development. This position paper posits that for AI systems to truly emulate or approach human-like interactions, especially within…

Thinking Tokens (TT) have been proposed as an unsupervised method to facilitate reasoning in language models. However, despite their conceptual appeal, our findings show that TTs marginally improves performance and consistently…

Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied to robotics, autonomous driving, and autoregressive text generation. The…

Reasoning with a chain-of-thought (CoT) enables Large Language Models (LLMs) to solve complex tasks but incurs significant inference costs due to the generation of long rationales. We propose Thinking States, a method that performs…

Enabling humans to identify potential flaws in an agent's decision making is an important Explainable AI application. We consider identifying such flaws in a planning-based deep reinforcement learning (RL) agent for a complex real-time…

This is the second in a series of short reports that seek to help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. In this report, we investigate Chain-of-Thought (CoT)…

Creative thinking is a fundamental aspect of human cognition, and divergent thinking-the capacity to generate novel and varied ideas-is widely regarded as its core generative engine. Large language models (LLMs) have recently demonstrated…

Reinforcement Learning (RL)-based post-training has significantly advanced the complex reasoning capabilities of language models, fostering sophisticated self-reflection processes. However, this ``slow thinking'' paradigm presents a…

Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful recipe for solving complex language tasks. In robotics, similar embodied CoT strategies,…

Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts. Imitation learning has emerged as one of the prominent approaches to build such…

Strategic reasoning enables agents to cooperate, communicate, and compete with other agents in diverse situations. Existing approaches to solving strategic games rely on extensive training, yielding strategies that do not generalize to new…