The making of knowledge engines in natural language processing has been shaped by two seemingly distinct paradigms: one grounded in structure, the other driven by massively available unstructured data. The structured paradigm leverages predefined symbolic interactions, such as knowledge graphs, as priors and designs models to capture them. In contrast, the unstructured paradigm centers on scaling transformer architectures with increasingly vast data and model sizes, as seen in modern large language models. Despite their divergence, this thesis seeks to establish conceptual connections bridging these paradigms. Two complementary forces, structure and destructure, emerge across both paradigms: structure organizes seen symbolic interactions, while destructure, through periodic embedding resets, improves model plasticity and generalization to unseen scenarios. These connections form a new recipe for developing general knowledge engines that can support transparent, controllable, and adaptable intelligent systems.

Humans intuitively navigate social interactions by simulating unspoken dynamics and reasoning about others' perspectives, even with limited information. In contrast, AI systems struggle to automatically structure and reason about these implicit social contexts. In this paper, we introduce a novel structured social world representation formalism (S3AP), designed to help AI systems reason more effectively about social dynamics. Following a POMDP-driven design, S3AP represents social interactions as structured tuples, such as state, observation, agent actions, and mental states, which can be automatically induced from free-form narratives or other inputs. We first show S3AP can help LLMs better understand social narratives across 5 social reasoning tasks (e.g., +51% improvement on FANToM's theory-of-mind reasoning with OpenAI's o1), reaching new state-of-the-art (SOTA) performance. We then induce social world models from these structured representations, demonstrating their ability to predict future social dynamics and improve agent decision-making, yielding up to +18% improvement on the SOTOPIA social interaction benchmark. Our findings highlight the promise of S3AP as a powerful, general-purpose representation for social world states, enabling the development of more socially-aware systems that better navigate social interactions.

Partially observable restless multi-armed bandits have found numerous applications including in recommendation systems, communication systems, public healthcare outreach systems, and in operations research. We study multi-action partially observable restless multi-armed bandits, it is a generalization of the classical restless multi-armed bandit problem -- 1) each bandit has finite states, and the current state is not observable, 2) each bandit has finite actions. In particular, we assume that more than two actions are available for each bandit. We motivate our problem with the application of public-health intervention planning. We describe the model and formulate a long term discounted optimization problem, where the state of each bandit evolves according to a Markov process, and this evolution is action dependent. The state of a bandit is not observable but one of finitely many feedback signals are observable. Each bandit yields a reward, based on the action taken on that bandit. The agent is assumed to have a budget constraint. The bandits are assumed to be independent. However, they are weakly coupled at the agent through the budget constraint. We first analyze the Lagrangian bound method for our partially observable restless bandits. The computation of optimal value functions for finite-state, finite-action POMDPs is non-trivial. Hence, the computation of Lagrangian bounds is also challenging. We describe approximations for the computation of Lagrangian bounds using point based value iteration (PBVI) and online rollout policy. We further present various properties of the value functions and provide theoretical insights on PBVI and online rollout policy. We study heuristic policies for multi-actions PORMAB. Finally, we discuss present Whittle index policies and their limitations in our model.

Traditional budget allocation models struggle with the stochastic and nonlinear nature of real-world financial data. This study proposes a hybrid reinforcement learning (RL) framework for dynamic budget allocation, enhanced with Dirichlet-inspired stochasticity and quantum mutation-based genetic optimization. Using Apple Inc. quarterly financial data (2009 to 2025), the RL agent learns to allocate budgets between Research and Development and Selling, General and Administrative to maximize profitability while adhering to historical spending patterns, with L2 penalties discouraging unrealistic deviations. A Dirichlet distribution governs state evolution to simulate shifting financial contexts. To escape local minima and improve generalization, the trained policy is refined using genetic algorithms with quantum mutation via parameterized qubit rotation circuits. Generation-wise rewards and penalties are logged to visualize convergence and policy behavior. On unseen fiscal data, the model achieves high alignment with actual allocations (cosine similarity 0.9990, KL divergence 0.0023), demonstrating the promise of combining deep RL, stochastic modeling, and quantum-inspired heuristics for adaptive enterprise budgeting.

Recent technological advances have expanded the availability of high-throughput biological datasets, enabling the reliable design of digital twins of biomedical systems or patients. Such computational tools represent key reaction networks driving perturbation or drug response and can guide drug discovery and personalized therapeutics. Yet, their development still relies on laborious data integration by the human modeler, so that automated approaches are critically needed. The success of data-driven system discovery in Physics, rooted in clean datasets and well-defined governing laws, has fueled interest in applying similar techniques in Biology, which presents unique challenges. Here, we reviewed methodologies for automatically inferring digital twins from biological time series, which mostly involve symbolic or sparse regression. We evaluate algorithms according to eight biological and methodological challenges, associated to noisy/incomplete data, multiple conditions, prior knowledge integration, latent variables, high dimensionality, unobserved variable derivatives, candidate library design, and uncertainty quantification. Upon these criteria, sparse regression generally outperformed symbolic regression, particularly when using Bayesian frameworks. We further highlight the emerging role of deep learning and large language models, which enable innovative prior knowledge integration, though the reliability and consistency of such approaches must be improved. While no single method addresses all challenges, we argue that progress in learning digital twins will come from hybrid and modular frameworks combining chemical reaction network-based mechanistic grounding, Bayesian uncertainty quantification, and the generative and knowledge integration capacities of deep learning. To support their development, we further propose a benchmarking framework to evaluate methods across all challenges.

Recent advances in reasoning and planning capabilities of large language models (LLMs) have enabled their potential as autonomous agents capable of tool use in dynamic environments. However, in multi-turn conversational environments like $τ$-bench, these agents often struggle with consistent reasoning, adherence to domain-specific policies, and extracting correct information over a long horizon of tool-calls and conversation. To capture and mitigate these failures, we conduct a comprehensive manual analysis of the common errors occurring in the conversation trajectories. We then experiment with reformulations of inputs to the tool-calling agent for improvement in agent decision making. Finally, we propose the Input-Reformulation Multi-Agent (IRMA) framework, which automatically reformulates user queries augmented with relevant domain rules and tool suggestions for the tool-calling agent to focus on. The results show that IRMA significantly outperforms ReAct, Function Calling, and Self-Reflection by 16.1%, 12.7%, and 19.1%, respectively, in overall pass^5 scores. These findings highlight the superior reliability and consistency of IRMA compared to other methods in dynamic environments.

Multimodal large language models (MLLMs) have emerged as pivotal tools in enhancing human-computer interaction. In this paper we focus on the application of MLLMs in the field of graphical user interface (GUI) elements structuring, where they assist in processing user instructions based on screen contents. Despite the promise of MLLMs, their performance in precisely generating UI element coordinates, a critical aspect of GUI understanding, is hindered by the nature of next-token prediction training. This challenge arises from the semantic void surrounding numerical UI coordinates in language representation spaces, necessitating a substantial and diverse dataset to bolster visual module capabilities. T o address these limitations, we introduce an IoU-Augmented Maximum Likelihood (IAML) training paradigm. Specifically, our approach involves a novel pipeline for IoU-based coordinate sampling to augment the training data, which considers the proximity to ground truth coordinates. This data augmentation strategy is then employed to fine-tune MLLMs under the IAML paradigm, which is designed to mitigate the exposure bias problem inherent in traditional maximum likelihood estimation. Through extensive experiments, we demonstrate the superior performance of our IAML training approach over traditional training paradigms.

-- Service robots operating in cluttered human environments such as homes, offices, and schools cannot rely on predefined object arrangements and must continuously update their semantic and spatial estimates while dealing with possible frequent rearrangements. Efficient and accurate mapping under such conditions demands selecting informative viewpoints and targeted manipulations to reduce occlusions and uncertainty. In this work, we present a manipulation-enhanced semantic mapping framework for occlusion-heavy shelf scenes that integrates evidential metric-semantic mapping with reinforcement-learning-based next-best view planning and targeted action selection. Our method thereby exploits uncertainty estimates from Dirichlet and Beta distributions in the map prediction networks to guide both active sensor placement and object manipulation, focusing on areas with high uncertainty and selecting actions with high expected information gain. Furthermore, we introduce an uncertainty-informed push strategy that targets occlusion-critical objects and generates minimally invasive actions to reveal hidden regions by reducing overall uncertainty in the scene. The experimental evaluation shows that our framework enables to accurately map cluttered scenes, while substantially reducing object displacement and achieving a 95% reduction in planning time compared to the state-of-the-art, thereby realizing real-world applicability. The successful deployment of general-purpose service robots in homes and offices relies on perceiving and manipulating diverse objects in cluttered and constrained spaces. Robots must move beyond passive perception (e.g., mapping with a static camera) and instead apply active perception [1] in combination with deliberate physical object interactions [2].

The move-acceptance hyper-heuristic was recently shown to be able to leave local optima with astonishing efficiency (Lissovoi et al., Artificial Intelligence (2023)). In this work, we propose two modifications to this algorithm that demonstrate impressive performances on a large class of benchmarks including the classic Cliff$_d$ and Jump$_m$ function classes. (i) Instead of randomly choosing between the only-improving and any-move acceptance operator, we take this choice via a simple two-state Markov chain. This modification alone reduces the runtime on Jump$_m$ functions with gap parameter $m$ from $Ω(n^{2m-1})$ to $O(n^{m+1})$. (ii) We then replace the all-moves acceptance operator with the operator that only accepts worsenings. Such a, counter-intuitive, operator has not been used before in the literature. However, our proofs show that our only-worsening operator can greatly help in leaving local optima, reducing, e.g., the runtime on Jump functions to $O(n^3 \log n)$ independent of the gap size. In general, we prove a remarkably good runtime of $O(n^{k+1} \log n)$ for our Markov move-acceptance hyper-heuristic on all members of a new benchmark class SEQOPT$_k$, which contains a large number of functions having $k$ successive local optima, and which contains the commonly studied Jump$_m$ and Cliff$_d$ functions for $k=2$.

Auditing the privacy leakage of synthetic data is an important but unresolved problem. Most existing privacy auditing frameworks for synthetic data rely on heuristics and unreasonable assumptions to attack the failure modes of generative models, exhibiting limited capability to describe and detect the privacy exposure of training data through synthetic data release. In this paper, we study designing Membership Inference Attacks (MIAs) that specifically exploit the observation that tabular generative models tend to significantly overfit to certain regions of the training distribution. Here, we propose Generative Likelihood Ratio Attack (Gen-LRA), a novel, computationally efficient No-Box MIA that, with no assumption of model knowledge or access, formulates its attack by evaluating the influence a test observation has in a surrogate model's estimation of a local likelihood ratio over the synthetic data. Assessed over a comprehensive benchmark spanning diverse datasets, model architectures, and attack parameters, we find that Gen-LRA consistently dominates other MIAs for generative models across multiple performance metrics. These results underscore Gen-LRA's effectiveness as a privacy auditing tool for the release of synthetic data, highlighting the significant privacy risks posed by generative model overfitting in real-world applications.