Related papers: Learning Representations and Agents for Informatio…
As large language models (LLMs) become more specialized, we envision a future where millions of expert LLMs exist, each trained on proprietary data and excelling in specific domains. In such a system, answering a query requires selecting a…
Large language models (LLMs) excel at natural language tasks but are limited by their static parametric knowledge, especially in knowledge-intensive task. Retrieval-augmented generation (RAG) mitigates this by integrating external…
When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…
To solve difficult tasks, humans ask questions to acquire knowledge from external sources. In contrast, classical reinforcement learning agents lack such an ability and often resort to exploratory behavior. This is exacerbated as few…
The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents that lack…
The rise of large language models (LLMs) has introduced a new era in information retrieval (IR), where queries and documents that were once assumed to be generated exclusively by humans can now also be created by automated agents. These…
Memory-augmented agents maintain multiple specialized stores, yet most systems retrieve from all stores for every query, increasing cost and introducing irrelevant context. We formulate memory retrieval as a store-routing problem and…
Information technology has profoundly altered the way humans interact with information. The vast amount of content created, shared, and disseminated online has made it increasingly difficult to access relevant information. Over the past two…
Successful negotiators must learn how to balance optimizing for self-interest and cooperation. Yet current artificial negotiation agents often heavily depend on the quality of the static datasets they were trained on, limiting their…
Continual learning refers to the ability of a biological or artificial system to seamlessly learn from continuous streams of information while preventing catastrophic forgetting, i.e., a condition in which new incoming information strongly…
A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguably do the…
Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects…
Building machines capable of efficiently collaborating with humans has been a longstanding goal in artificial intelligence. Especially in the presence of uncertainties, optimal cooperation often requires that humans and artificial agents…
It is quite popular nowadays for researchers and data analysts holding different datasets to seek assistance from each other to enhance their modeling performance. We consider a scenario where different learners hold datasets with…
Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused -- strategic machines might craft representations that manipulate their users. How can a user make good…
Large language models can perform well on many isolated tasks, yet they continue to struggle on multi-turn, long-horizon agentic problems that require skills such as planning, state tracking, and long context processing. In this work, we…
In order to bring artificial agents into our lives, we will need to go beyond supervised learning on closed datasets to having the ability to continuously expand knowledge. Inspired by a student learning in a classroom, we present an agent…
Almost all the knowledge empowered applications rely upon accurate knowledge, which has to be either collected manually with high cost, or extracted automatically with unignorable errors. In this paper, we study 20 Questions, an online…
The paper presents an approach to build a question and answer system that is capable of processing the information in a large dataset and allows the user to gain knowledge from this dataset by asking questions in natural language form. Key…
Objective: Information retrieval (IR, also known as search) systems are ubiquitous in modern times. How does the emergence of generative artificial intelligence (AI), based on large language models (LLMs), fit into the IR process? Process:…