Learning visuomotor policies via imitation has proven effective across a wide range of robotic domains. However, the performance of these policies is heavily dependent on the number of training demonstrations, which requires expensive data collection in the real world. In this work, we aim to reduce data collection efforts when learning visuomotor robot policies by leveraging existing or cost-effective data from a wide range of embodiments, such as public robot datasets and the datasets of humans playing with objects (human data from play). Our approach leverages two key insights. First, we use optic flow as an embodiment-agnostic action representation to train a World Model (WM) across multi-embodiment datasets, and finetune it on a small amount of robot data from the target embodiment. Second, we develop a method, Latent Policy Steering (LPS), to improve the output of a behavior-cloned policy by searching in the latent space of the WM for better action sequences. In real world experiments, we observe significant improvements in the performance of policies trained with a small amount of data (over 50% relative improvement with 30 demonstrations and over 20% relative improvement with 50 demonstrations) by combining the policy with a WM pretrained on two thousand episodes sampled from the existing Open X-embodiment dataset across different robots or a cost-effective human dataset from play.

Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffer from inefficiencies in multi-turn interactions, frequently trapped in repetitive loops or issuing ineffective commands, leading to redundant computational overhead. Instead of relying solely on learning from trajectories, we take a first step toward exploring the early-exit behavior for LLM-based agents. We propose two complementary approaches: 1. an $\textbf{intrinsic}$ method that injects exit instructions during generation, and 2. an $\textbf{extrinsic}$ method that verifies task completion to determine when to halt an agent's trial. To evaluate early-exit mechanisms, we introduce two metrics: one measures the reduction of $\textbf{redundant steps}$ as a positive effect, and the other evaluates $\textbf{progress degradation}$ as a negative effect. Experiments with 4 different LLMs across 5 embodied environments show significant efficiency improvements, with only minor drops in agent performance. We also validate a practical strategy where a stronger agent assists after an early-exit agent, achieving better performance with the same total steps. We will release our code to support further research.

Atomic data determined by analysis of observed atomic spectra are essential for plasma diagnostics. For each low-ionisation open d- and f-subshell atomic species, around $10^3$ fine structure level energies can be determined through years of analysis of $10^4$ observable spectral lines. We propose the automation of this task by casting the analysis procedure as a Markov decision process and solving it by graph reinforcement learning using reward functions learned on historical human decisions. In our evaluations on existing spectral line lists and theoretical calculations for Co II and Nd II-III, hundreds of level energies were computed within hours, agreeing with published values in 95% of cases for Co II and 54-87% for Nd II-III. As the current efficiency in atomic fine structure determination struggles to meet growing atomic data demands from astronomy and fusion science, our new artificial intelligence approach sets the stage for closing this gap.

Deep reinforcement learning (RL) is emerging as a viable strategy for automated cyber defense (ACD). The traditional RL approach represents networks as a list of computers in various states of safety or threat. Unfortunately, these models are forced to overfit to specific network topologies, rendering them ineffective when faced with even small environmental perturbations. In this work, we frame ACD as a two-player context-based partially observable Markov decision problem with observations represented as attributed graphs. This approach allows our agents to reason through the lens of relational inductive bias. Agents learn how to reason about hosts interacting with other system entities in a more general manner, and their actions are understood as edits to the graph representing the environment. By introducing this bias, we will show that our agents can better reason about the states of networks and zero-shot adapt to new ones. We show that this approach outperforms the state-of-the-art by a wide margin, and makes our agents capable of defending never-before-seen networks against a wide range of adversaries in a variety of complex, and multi-agent environments.

A fully quantum reinforcement learning framework is developed that integrates a quantum Markov decision process, dynamic circuit-based qubit reuse, and Grover's algorithm for trajectory optimization. The framework encodes states, actions, rewards, and transitions entirely within the quantum domain, enabling parallel exploration of state-action sequences through superposition and eliminating classical subroutines. Dynamic circuit operations, including mid-circuit measurement and reset, allow reuse of the same physical qubits across multiple agent-environment interactions, reducing qubit requirements from 7*T to 7 for T time steps while preserving logical continuity. Quantum arithmetic computes trajectory returns, and Grover's search is applied to the superposition of these evaluated trajectories to amplify the probability of measuring those with the highest return, thereby accelerating the identification of the optimal policy. Simulations demonstrate that the dynamic-circuit-based implementation preserves trajectory fidelity while reducing qubit usage by 66 percent relative to the static design. Experimental deployment on IBM Heron-class quantum hardware confirms that the framework operates within the constraints of current quantum processors and validates the feasibility of fully quantum multi-step reinforcement learning under noisy intermediate-scale quantum conditions. This framework advances the scalability and practical application of quantum reinforcement learning for large-scale sequential decision-making tasks.

The primary objective of RL is for an agent to learn an optimal policy to control a system by minimizing a long-term loss, represented by the Q-function. This learning occurs through interactions with the environment, which is typically modeled as a Markov decision process (MDP). In most high-dimensional, real-world problems, explicitly representing the Q-function for all possible states and actions is impractical due to the "curse of dimensionality." A common solution is to approximate the Q-function using a parametric (functional) representation. This, however, introduces a fundamental trade-off between approximation accuracy and computational complexity: reducing the approximation error generally requires a large number of features in the parametric model, which in turn increases computational demands. Feature selection, achieved via a sparse representation over a large basis of functions, is an effective way to alleviate this tradeoff, mitigate overfitting, and improve sample efficiency.

This paper studies fully decentralized cooperative multi-agent reinforcement learning, where each agent solely observes the states, its local actions, and the shared rewards. The inability to access other agents' actions often leads to non-stationarity during value function updates and relative overgeneralization during value function estimation, hindering effective cooperative policy learning. However, existing works fail to address both issues simultaneously, due to their inability to model the joint policy of other agents in a fully decentralized setting. To overcome this limitation, we propose a novel method named Dynamics-A ware Context (DAC), which formalizes the task, as locally perceived by each agent, as an Contextual Markov Decision Process, and further addresses both non-stationarity and relative overgeneralization through dynamics-aware context modeling. Specifically, DAC attributes the non-stationary local task dynamics of each agent to switches between unobserved contexts, each corresponding to a distinct joint policy. Then, DAC models the step-wise dynamics distribution using latent variables and refers to them as contexts. For each agent, DAC introduces a context-based value function to address the non-stationarity issue during value function update. For value function estimation, an optimistic marginal value is derived to promote the selection of cooperative actions, thereby addressing the relative overgeneralization issue. Experimentally, we evaluate DAC on various cooperative tasks (including matrix game, predator and prey, and SMAC), and its superior performance against multiple baselines validates its effectiveness.

Online planning in Markov Decision Processes (MDPs) enables agents to make sequential decisions by simulating future trajectories from the current state, making it well-suited for large-scale or dynamic environments. Sample-based methods such as Sparse Sampling and Monte Carlo Tree Search (MCTS) are widely adopted for their ability to approximate optimal actions using a generative model. However, in practical settings, the generative model is often learned from limited data, introducing approximation errors that can degrade performance or lead to unsafe behaviors. To address these challenges, Robust MDPs (RMDPs) offer a principled framework for planning under model uncertainty, yet existing approaches are typically computationally intensive and not suited for real-time use. In this work, we introduce Robust Sparse Sampling (RSS), the first online planning algorithm for RMDPs with finite-sample theoretical performance guarantees. Unlike Sparse Sampling, which estimates the nominal value function, RSS computes a robust value function by leveraging the efficiency and theoretical properties of Sample Average Approximation (SAA), enabling tractable robust policy computation in online settings. RSS is applicable to infinite or continuous state spaces, and its sample and computational complexities are independent of the state space size. We provide theoretical performance guarantees and empirically show that RSS outperforms standard Sparse Sampling in environments with uncertain dynamics.

We argue that ontology - structured knowledge graphs can play a crucial role in generating predictions about future events. By leveraging the semantic framework provided by Basic Formal Ontology (BFO) and Common Core Ontologies (CCO), we demonstrate how data -- such as the movements of a fishing vessel -- can be organ ized in and retrieved from a knowledge graph. These query results are then used to create Markov chain models, allowing us to predict future states based on the vessel's history. To fully support this process, we introduce the term `spatiotemporal instant' to complete the necessary structural semantics. Additionally, we critique the prevailing ontological model of probability, according to which probabilities are about the future . We propose an alternative view, where at least some probabilities are treated as being about actual process profiles, which better captures the dynamics of real - world phenomena. Finally, we demonstrate how our Markov chain - based probability calculations can be seamlessly integrated back into the knowledge graph, enabling further an alysis and decision - making.

As large language models (LLMs) become integral to multi-agent systems, new privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations. In particular, seemingly innocuous responses, when composed across interactions, can cumulatively enable adversaries to recover sensitive information, a phenomenon we term compositional privacy leakage. We present the first systematic study of such compositional privacy leaks and possible mitigation methods in multi-agent LLM systems. First, we develop a framework that models how auxiliary knowledge and agent interactions jointly amplify privacy risks, even when each response is benign in isolation. Next, to mitigate this, we propose and evaluate two defense strategies: (1) Theory-of-Mind defense (ToM), where defender agents infer a questioner's intent by anticipating how their outputs may be exploited by adversaries, and (2) Collaborative Consensus Defense (CoDef), where responder agents collaborate with peers who vote based on a shared aggregated state to restrict sensitive information spread. Crucially, we balance our evaluation across compositions that expose sensitive information and compositions that yield benign inferences. Our experiments quantify how these defense strategies differ in balancing the privacy-utility trade-off. We find that while chain-of-thought alone offers limited protection to leakage (~39% sensitive blocking rate), our ToM defense substantially improves sensitive query blocking (up to 97%) but can reduce benign task success. CoDef achieves the best balance, yielding the highest Balanced Outcome (79.8%), highlighting the benefit of combining explicit reasoning with defender collaboration. Together, our results expose a new class of risks in collaborative LLM deployments and provide actionable insights for designing safeguards against compositional, context-driven privacy leakage.