Reasoning models (RMs), language models (LMs) trained with reinforcement learning to produce long-form natural language reasoning, have been remarkably successful, but they still require large amounts of computation and data to train, and can be slow and expensive to run. In this paper, we show that standard instruct LMs can already be elicited to be strong reasoners at a level comparable to or even surpassing their corresponding RMs (e.g., DeepSeek V3 vs R1) without finetuning, across diverse domains from instruction following and creative generation to mathematical reasoning. This is achieved by CodeAdapt, our simple recipe that combines the CodeAct framework, where LMs interleave natural language reasoning with code execution in a multi-step fashion, with few-shot bootstrap in-context learning from as few as five training problems. Analyzing four matched pairs of LMs and RMs, we find that CodeAdapt enables three LMs to outperform the corresponding RMs on average over eight tasks (up to 22.9%) while being 10-81% more token efficient, and delivers superior performance on six tasks when averaged over the four models (up to 35.7%). Furthermore, the code-augmented reasoning traces display rich and varied problem-solving strategies. Our findings support that (1) CodeAdapt-style learning and reasoning may be robust and domain general and (2) code-enabled LMs are cognitively grounded and powerful systems, potentially providing a strong foundation for in-weight reinforcement learning.

Generalization is a key challenge in machine learning, specifically in reasoning tasks, where models are expected to solve problems more complex than those encountered during training. Existing approaches typically train reasoning models in an end-to-end fashion, directly mapping input instances to solutions. While this allows models to learn useful heuristics from data, it often results in limited generalization beyond the training distribution. In this work, we propose a novel approach to reasoning generalization by learning energy landscapes over the solution spaces of smaller, more tractable subproblems. At test time, we construct a global energy landscape for a given problem by combining the energy functions of multiple subproblems. This compositional approach enables the incorporation of additional constraints during inference, allowing the construction of energy landscapes for problems of increasing difficulty. To improve the sample quality from this newly constructed energy landscape, we introduce Parallel Energy Minimization (PEM). We evaluate our approach on a wide set of reasoning problems. Our method outperforms existing state-of-the-art methods, demonstrating its ability to generalize to larger and more complex problems. Project website can be found at: https://alexoarga.github.io/compositional_reasoning/

We propose and evaluate a quantum-inspired algorithm for solving Quadratic Unconstrained Binary Optimization (QUBO) problems, which are mathematically equivalent to finding ground states of Ising spin-glass Hamiltonians. The algorithm employs Matrix Product States (MPS) to compactly represent large superpositions of spin configurations and utilizes a discrete driving schedule to guide the MPS toward the ground state. At each step, a driver Hamiltonian -- incorporating a transverse magnetic field -- is combined with the problem Hamiltonian to enable spin flips and facilitate quantum tunneling. The MPS is updated using the standard Density Matrix Renormalization Group (DMRG) method, which iteratively minimizes the system's energy via multiple sweeps across the spin chain. Despite its heuristic nature, the algorithm reliably identifies global minima, not merely near-optimal solutions, across diverse QUBO instances. We first demonstrate its effectiveness on intermediate-level Sudoku puzzles from publicly available sources, involving over $200$ Ising spins with long-range couplings dictated by constraint satisfaction. We then apply the algorithm to MaxCut problems from the Biq Mac library, successfully solving instances with up to $251$ nodes and $3,265$ edges. We discuss the advantages of this quantum-inspired approach, including its scalability, generalizability, and suitability for industrial-scale QUBO applications.

A new strategy for fair supervised machine learning is proposed. The main advantages of the proposed strategy as compared to others in the literature are as follows. (a) We introduce a new smooth nonconvex surrogate to approximate the Heaviside functions involved in discontinuous unfairness measures. The surrogate is based on smoothing methods from the optimization literature, and is new for the fair supervised learning literature. The surrogate is a tight approximation which ensures the trained prediction models are fair, as opposed to other (e.g., convex) surrogates that can fail to lead to a fair prediction model in practice. (b) Rather than rely on regularizers (that lead to optimization problems that are difficult to solve) and corresponding regularization parameters (that can be expensive to tune), we propose a strategy that employs hard constraints so that specific tolerances for unfairness can be enforced without the complications associated with the use of regularization. (c) Our proposed strategy readily allows for constraints on multiple (potentially conflicting) unfairness measures at the same time. Multiple measures can be considered with a regularization approach, but at the cost of having even more difficult optimization problems to solve and further expense for tuning. By contrast, through hard constraints, our strategy leads to optimization models that can be solved tractably with minimal tuning.

Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance: methods that tightly enforce safety often cripple task performance, while those that prioritize reward leave safety constraints frequently violated, producing diffuse cost landscapes that flatten gradients and stall policy improvement. We introduce the Uncertain Safety Critic (USC), a novel approach that integrates uncertainty-aware modulation and refinement into critic training. By concentrating conservatism in uncertain and costly regions while preserving sharp gradients in safe areas, USC enables policies to achieve effective reward-safety trade-offs. Extensive experiments show that USC reduces safety violations by approximately 40% while maintaining competitive or higher rewards, and reduces the error between predicted and true cost gradients by approximately 83%, breaking the prevailing trade-off between safety and performance and paving the way for scalable safe RL.

Imitation learning from large-scale, diverse human demonstrations has proven effective for training robots, but collecting such data is costly and time-consuming. This challenge is amplified for multi-step bimanual mobile manipulation, where humans must teleoperate both a mobile base and two high-degree-of-freedom arms. Prior automated data generation frameworks have addressed static bimanual manipulation by augmenting a few human demonstrations in simulation, but they fall short for mobile settings due to two key challenges: (1) determining base placement to ensure reachability, and (2) positioning the camera to provide sufficient visibility for visuomotor policies. To address these issues, we introduce MoMaGen, which formulates data generation as a constrained optimization problem that enforces hard constraints (e.g., reachability) while balancing soft constraints (e.g., visibility during navigation). This formulation generalizes prior approaches and provides a principled foundation for future methods. We evaluate MoMaGen on four multi-step bimanual mobile manipulation tasks and show that it generates significantly more diverse datasets than existing methods. Leveraging this diversity, MoMaGen can train successful imitation learning policies from a single source demonstration, and these policies can be fine-tuned with as few as 40 real-world demonstrations to achieve deployment on physical robotic hardware. More details are available at our project page: momagen.github.io.

The reliable execution of high-level missions in multi-robot systems with heterogeneous agents, requires robust methods for detecting spurious behaviors. In this paper, we address the challenge of identifying spurious executions of plans specified as a Linear Temporal Logic (LTL) formula, as incorrect task sequences, violations of spatial constraints, timing inconsis- tencies, or deviations from intended mission semantics. To tackle this, we introduce a structured data generation framework based on the Nets-within-Nets (NWN) paradigm, which coordinates robot actions with LTL-derived global mission specifications. We further propose a Transformer-based anomaly detection pipeline that classifies robot trajectories as normal or anomalous. Experi- mental evaluations show that our method achieves high accuracy (91.3%) in identifying execution inefficiencies, and demonstrates robust detection capabilities for core mission violations (88.3%) and constraint-based adaptive anomalies (66.8%). An ablation experiment of the embedding and architecture was carried out, obtaining successful results where our novel proposition performs better than simpler representations.

Assembly hinges on reliably forming connections between parts; yet most robotic approaches plan assembly sequences and part poses while treating connectors as an afterthought. Connections represent the critical "last mile" of assembly execution, while task planning may sequence operations and motion plan may position parts, the precise establishment of physical connections ultimately determines assembly success or failure. In this paper, we consider connections as first-class primitives in assembly representation, including connector types, specifications, quantities, and placement locations. Drawing inspiration from how humans learn assembly tasks through step-by-step instruction manuals, we present Manual2Skill++, a vision-language framework that automatically extracts structured connection information from assembly manuals. We encode assembly tasks as hierarchical graphs where nodes represent parts and sub-assemblies, and edges explicitly model connection relationships between components. A large-scale vision-language model parses symbolic diagrams and annotations in manuals to instantiate these graphs, leveraging the rich connection knowledge embedded in human-designed instructions. We curate a dataset containing over 20 assembly tasks with diverse connector types to validate our representation extraction approach, and evaluate the complete task understanding-to-execution pipeline across four complex assembly scenarios in simulation, spanning furniture, toys, and manufacturing components with real-world correspondence.

Modern manufacturing systems must meet hard delivery deadlines while coping with stochastic task durations caused by process noise, equipment variability, and human intervention. Traditional deterministic schedules break down when reality deviates from nominal plans, triggering costly last-minute repairs. This thesis combines offline constraint-programming (CP) optimisation with online temporal-network execution to create schedules that remain feasible under worst-case uncertainty. First, we build a CP model of the flexible job-shop with per-job deadline tasks and insert an optimal buffer $Δ^*$ to obtain a fully pro-active baseline. We then translate the resulting plan into a Simple Temporal Network with Uncertainty (STNU) and verify dynamic controllability, which guarantees that a real-time dispatcher can retime activities for every bounded duration realisation without violating resource or deadline constraints. Extensive Monte-Carlo simulations on the open Kacem~1--4 benchmark suite show that our hybrid approach eliminates 100\% of deadline violations observed in state-of-the-art meta-heuristic schedules, while adding only 3--5\% makespan overhead. Scalability experiments confirm that CP solve-times and STNU checks remain sub-second on medium-size instances. The work demonstrates how temporal-network reasoning can bridge the gap between proactive buffering and dynamic robustness, moving industry a step closer to truly digital, self-correcting factories.

The E-commerce advertising platforms typically sell commercial traffic through either second-price auction (SPA) or first-price auction (FPA). SPA was historically prevalent due to its dominant strategy incentive-compatible (DSIC) for bidders with quasi-linear utilities, especially when budgets are not a binding constraint, while FPA has gained more prominence for offering higher revenue potential to publishers and avoiding the possibility for discriminatory treatment in personalized reserve prices. Meanwhile, on the demand side, advertisers are increasingly adopting platform-wide marketing solutions akin to QuanZhanTui, shifting from spending budgets solely on commercial traffic to bidding on the entire traffic for the purpose of maximizing overall sales. For automated bidding systems, such a trend poses a critical challenge: determining optimal strategies across heterogeneous auction channels to fulfill diverse advertiser objectives, such as maximizing return (MaxReturn) or meeting target return on ad spend (TargetROAS). To overcome this challenge, this work makes two key contributions. First, we derive an efficient solution for optimal bidding under FPA channels, which takes into account the presence of organic traffic - traffic can be won for free. Second, we introduce a marginal cost alignment (MCA) strategy that provably secures bidding efficiency across heterogeneous auction mechanisms. To validate performance of our developed framework, we conduct comprehensive offline experiments on public datasets and large-scale online A/B testing, which demonstrate consistent improvements over existing methods.