相关论文: Deriving Character Logic from Storyline as Codifie…

Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead…

Reward design for reinforcement learning agents can be difficult in situations where one not only wants the agent to achieve some effect in the world but where one also cares about how that effect is achieved. For example, we might wish for…

Domestic and service robots have the potential to transform industries such as health care and small-scale manufacturing, as well as the homes in which we live. However, due to the overwhelming variety of tasks these robots will be expected…

Randomized Controlled Trials (RCTs), or A/B testing, have become the gold standard for optimizing various operational policies on online platforms. However, RCTs on these platforms typically cover a limited number of discrete treatment…

The human ability of deep cognitive skills are crucial for the development of various real-world applications that process diverse and abundant user generated input. While recent progress of deep learning and natural language processing…

Rule-based models, e.g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity. However, rule-based models are hard to optimize, especially on…

Deep neural networks have been proven powerful at processing perceptual data, such as images and audio. However for tabular data, tree-based models are more popular. A nice property of tree-based models is their natural interpretability. In…

LLM-based agentic coding assistants lack persistent memory: they lose coherence across sessions, forget project conventions, and repeat known mistakes. Recent studies characterize how developers configure agents through manifest files, but…

Behavior Trees (BT) are becoming increasingly popular in the robotics community. The BT tool is well suited for decision-making applications allowing a robot to perform complex behavior while being explainable to humans as well. Verifying…

Understanding cognitive processes in multi-agent interactions is a primary goal in cognitive science. It can guide the direction of artificial intelligence (AI) research toward social decision-making in multi-agent systems, which includes…

Offline reinforcement learning (RL) holds great promise for deriving optimal policies from observational data, but challenges related to interpretability and evaluation limit its practical use in safety-critical domains. Interpretability is…

We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…

Storytelling is fundamental to language, including culture, conversation and communication in their broadest senses. It thus emerges as an essential component of intelligent systems, including systems where natural language is not a primary…

Robots need task planning to sequence and execute actions toward achieving their goals. On the other hand, Behavior Trees provide a mathematical model for specifying plan execution in an intrinsically composable, reactive, and robust way.…

Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the environment. We aim to tackle a more challenging problem: learning a safe policy from an offline dataset. We study the offline safe RL problem…

Current role-playing agents (RPAs) are typically constructed by imitating surface-level behaviors, but this approach lacks internal cognitive consistency, often causing out-of-character errors in complex situations. To address this, we…

Our goal is to identify the features that predict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations. Previous attempts to devise rules for text generation…

Agentic discovery has shown that LLM-driven search can find novel algorithms, designs, and code under benchmark conditions. Translating the paradigm to multi-system data backends surfaces a harder problem: the search space is heterogeneous,…

Speech encodes a wealth of information related to human behavior and has been used in a variety of automated behavior recognition tasks. However, extracting behavioral information from speech remains challenging including due to inadequate…

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…