Related papers: Rejecting Hallucinated State Targets during Planni…
Semi-supervised learning methods based on generative adversarial networks (GANs) obtained strong empirical results, but it is not clear 1) how the discriminator benefits from joint training with a generator, and 2) why good semi-supervised…
Planning is a data efficient decision-making strategy where an agent selects candidate actions by exploring possible future states. To simulate future states when there is a high-dimensional action space, the knowledge of one's decision…
If we could define the set of all bad outcomes, we could hard-code an agent which avoids them; however, in sufficiently complex environments, this is infeasible. We do not know of any general-purpose approaches in the literature to avoiding…
Recent work has shown how predictive modeling can endow agents with rich knowledge of their surroundings, improving their ability to act in complex environments. We propose question-answering as a general paradigm to decode and understand…
A frequently observed problem with LLMs is their tendency to generate output that is nonsensical, illogical, or factually incorrect, often referred to broadly as hallucination. Building on the recently proposed HalluciGen task for…
Hallucinations pose critical risks for large language model (LLM)-based agents, often manifesting as hallucinative actions resulting from fabricated or misinterpreted information within the cognitive context. While recent studies have…
The premise of this working paper is based around agent-based simulation models and how to go about creating them from given incomplete information. Agent-based simulations are stochastic simulations that revolve around groups of agents…
Hallucinations remain a significant challenge in current Generative AI models, undermining trust in AI systems and their reliability. This study investigates how orchestrating multiple specialized Artificial Intelligent Agents can help…
Reduced models of large Markov decision processes accelerate planning by considering a subset of outcomes for each state-action pair. This reduction in reachable states leads to replanning when the agent encounters states without a…
To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environment that applies to new tasks. Similarly, skills capture…
Can machine learning models for recommendation be easily fooled? While the question has been answered for hand-engineered fake user profiles, it has not been explored for machine learned adversarial attacks. This paper attempts to close…
Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with language models, the…
Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained…
Traditional architectural simulations (e.g. Computational Fluid Dynamics, evacuation, structural analysis) model elements as deterministic physics-based "particles" rather than cognitive "agents". To bridge this, we introduce…
In designing multiple-choice questions (MCQs) in education, creating plausible distractors is crucial for identifying students' misconceptions and gaps in knowledge and accurately assessing their understanding. However, prior studies on…
Active inference provides a general framework for behavior and learning in autonomous agents. It states that an agent will attempt to minimize its variational free energy, defined in terms of beliefs over observations, internal states and…
Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent description of existing behavior in the first place. In this paper, we develop an expressive,…
We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a methodology based on concept-based interpretability to a model-free agent in Sokoban -- a commonly…
Despite improvements in performances on different natural language generation tasks, deep neural models are prone to hallucinating facts that are incorrect or nonexistent. Different hypotheses are proposed and examined separately for…
This paper presents a computational model of how conversational participants collaborate in order to make a referring action successful. The model is based on the view of language as goal-directed behavior. We propose that the content of a…