Related papers: Communicating Natural Programs to Humans and Machi…
Large language model (LLM) agent evaluators leverage specialized tools to ground the rational decision-making of LLMs, making them well-suited to aid in scientific discoveries, such as constrained retrosynthesis planning. Constrained…
A natural language (or ordinary language) is a language that is spoken, written, or signed by humans for general-purpose communication, as distinguished from formal languages (such as computer-programming languages or the "languages" used…
Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite of a long history of research on constructing AI systems with these…
We explore the applicability of text-to-code to solve real-world problems that are typically solved in natural language, such as legal judgment and medical QA. Unlike previous works, our approach leverages the explicit reasoning provided by…
The integration of generative Artificial Intelligence (genAI) into everyday life raises questions about the competencies required to critically engage with these technologies. Unlike visual errors in genAI, textual mistakes are often harder…
We have a vision of a day when autonomous robots can collaborate with humans as assistants in performing complex tasks in the physical world. This vision includes that the robots will have the ability to communicate with their human…
Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning.…
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.…
A central but unresolved aspect of problem-solving in AI is the capability to introduce and use abstractions, something humans excel at. Work in cognitive science has demonstrated that humans tend towards higher levels of abstraction when…
Today's conversational agents are restricted to simple standalone commands. In this paper, we present Iris, an agent that draws on human conversational strategies to combine commands, allowing it to perform more complex tasks that it has…
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…
Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire…
Cellular automata and their differentiable counterparts, Neural Cellular Automata (NCA), are highly expressive and capable of surprisingly complex behaviors. This paper explores how NCAs perform when applied to tasks requiring precise…
Though LLMs are capable of generating plausible programs, it's challenging to interact with the LLMs further to revise the program, especially if the user's specific requirements are different from the initial proposal. In this paper, we…
Systematic Literature Reviews (SLRs) are fundamental to scientific progress, yet the process is hindered by a fragmented tool ecosystem that imposes a high cognitive load. This friction suppresses the iterative, exploratory nature of…
A new generation of AI models generates step-by-step reasoning text before producing an answer. This text appears to offer a human-readable window into their computation process, and is increasingly relied upon for transparency and…
Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of its resemblance to how humans and animals acquire skills…
Even though intelligent systems such as Siri or Google Assistant are enjoyable (and useful) dialog partners, users can only access predefined functionality. Enabling end-users to extend the functionality of intelligent systems will be the…
Over the years, access control systems have become increasingly more complex, often causing a disconnect between what is envisaged by the stakeholders in decision-making positions and the actual permissions granted as evidenced from access…
We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates…