Monitoring AIs at runtime can help us detect and stop harmful actions. In this paper, we study how to efficiently combine multiple runtime monitors into a single monitoring protocol. The protocol's objective is to maximize the probability of applying a safety intervention on misaligned outputs (i.e., maximize recall). Since running monitors and applying safety interventions are costly, the protocol also needs to adhere to an average-case budget constraint. Taking the monitors' performance and cost as given, we develop an algorithm to find the best protocol. The algorithm exhaustively searches over when and which monitors to call, and allocates safety interventions based on the Neyman-Pearson lemma. By focusing on likelihood ratios and strategically trading off spending on monitors against spending on interventions, we more than double our recall rate compared to a naive baseline in a code review setting. We also show that combining two monitors can Pareto dominate using either monitor alone. Our framework provides a principled methodology for combining existing monitors to detect undesirable behavior in cost-sensitive settings.

Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two contrasting advantage estimation granularities: token-level methods (e.g., PPO) aim to provide fine-grained advantage signals but suffer from inaccurate estimation due to difficulties in training an accurate critic model. On the other extreme, trajectory-level methods (e.g., GRPO) solely rely on a coarse-grained advantage signal from the final reward, leading to imprecise credit assignment. To address these limitations, we propose Segment Policy Optimization (SPO), a novel RL framework that leverages segment-level advantage estimation at an intermediate granularity, achieving a better balance by offering more precise credit assignment than trajectory-level methods and requiring fewer estimation points than token-level methods, enabling accurate advantage estimation based on Monte Carlo (MC) without a critic model. SPO features three components with novel strategies: (1) flexible segment partition; (2) accurate segment advantage estimation; and (3) policy optimization using segment advantages, including a novel probability-mask strategy. We further instantiate SPO for two specific scenarios: (1) SPO-chain for short chain-of-thought (CoT), featuring novel cutpoint-based partition and chain-based advantage estimation, achieving $6$-$12$ percentage point improvements in accuracy over PPO and GRPO on GSM8K. (2) SPO-tree for long CoT, featuring novel tree-based advantage estimation, which significantly reduces the cost of MC estimation, achieving $7$-$11$ percentage point improvements over GRPO on MATH500 under 2K and 4K context evaluation. We make our code publicly available at https://github.com/AIFrameResearch/SPO.

Meta-Black-Box Optimization (MetaBBO) streamlines the automation of optimization algorithm design through meta-learning. It typically employs a bi-level structure: the meta-level policy undergoes meta-training to reduce the manual effort required in developing algorithms for low-level optimization tasks. The original MetaBox (2023) provided the first open-source framework for reinforcement learning-based single-objective MetaBBO. However, its relatively narrow scope no longer keep pace with the swift advancement in this field. In this paper, we introduce MetaBox-v2 (https://github.com/MetaEvo/MetaBox) as a milestone upgrade with four novel features: 1) a unified architecture supporting RL, evolutionary, and gradient-based approaches, by which we reproduce $23$ up-to-date baselines; 2) efficient parallelization schemes, which reduce the training/testing time by $10-40$x; 3) a comprehensive benchmark suite of $18$ synthetic/realistic tasks ($1900$+ instances) spanning single-objective, multi-objective, multi-model, and multi-task optimization scenarios; 4) plentiful and extensible interfaces for custom analysis/visualization and integrating to external optimization tools/benchmarks. To show the utility of MetaBox-v2, we carry out a systematic case study that evaluates the built-in baselines in terms of the optimization performance, generalization ability and learning efficiency. Valuable insights are concluded from thorough and detailed analysis for practitioners and those new to the field.

We introduce \textbf{BO4Mob}, a new benchmark framework for high-dimensional Bayesian Optimization (BO), driven by the challenge of origin-destination (OD) travel demand estimation in large urban road networks. Estimating OD travel demand from limited traffic sensor data is a difficult inverse optimization problem, particularly in real-world, large-scale transportation networks. This problem involves optimizing over high-dimensional continuous spaces where each objective evaluation is computationally expensive, stochastic, and non-differentiable. BO4Mob comprises five scenarios based on real-world San Jose, CA road networks, with input dimensions scaling up to 10,100. These scenarios utilize high-resolution, open-source traffic simulations that incorporate realistic nonlinear and stochastic dynamics. We demonstrate the benchmark's utility by evaluating five optimization methods: three state-of-the-art BO algorithms and two non-BO baselines. This benchmark is designed to support both the development of scalable optimization algorithms and their application for the design of data-driven urban mobility models, including high-resolution digital twins of metropolitan road networks. Code and documentation are available at https://github.com/UMN-Choi-Lab/BO4Mob.

Multimodal dataset distillation aims to synthesize a small set of image-text pairs that enables efficient training of large-scale vision-language models. While dataset distillation has shown promise in unimodal tasks, extending it to multimodal contrastive learning presents key challenges: learning cross-modal alignment and managing the high computational cost of large encoders. Prior approaches address scalability by freezing the text encoder and update only the image encoder and text projection layer. However, we find this severely limits semantic alignment and becomes a bottleneck for performance scaling. We propose CovMatch, a scalable dataset distillation framework that aligns the cross-covariance of real and synthetic features while regularizing feature distributions within each modality. Unlike prior approaches, CovMatch enables joint optimization of both encoders, leading to stronger cross-modal alignment and improved performance. Evaluated on Flickr30K and COCO, CovMatch outperforms state-of-the-art multimodal distillation methods and achieves up to 6.8% absolute gains in retrieval accuracy using only 500 synthetic pairs.

Feature selection is a combinatorial optimization problem that is NP -hard. Conventional approaches often employ heuristic or greedy strategies, which are prone to premature convergence and may fail to capture subtle yet informative features. This limitation becomes especially critical in high - dimensional datasets, where complex and interdependent feature relationships prevail. We introduce the HeFS (Helper - Enhanced Feature Selection) framework to refine feature subsets produced by existing algorithms. HeFS systematically searches the residual feature space to identify a Helper Set-- features that complement the original subset and improve classification performance. The approach employs a biased initialization scheme and a ratio-guided mutation mechanism within a genetic algorithm, coupled with Pareto - based multi - objective optimization to jointly maximize predictive accuracy and feature complementarity. Experiments on 18 benchmark datasets demonstrate that HeFS consistently identifies overlooked yet informative features and achieves superior performance over state-of-the - art methods, including in challenging domains such as gastric cancer classification, drug toxicity prediction, and computer science applications.

Efficient sampling from high-dimensional and multimodal unnormalized probability distributions is a central challenge in many areas of science and machine learning. We focus on Boltzmann generators (BGs) that aim to sample the Boltzmann distribution of physical systems, such as molecules, at a given temperature. Classical variational approaches that minimize the reverse Kullback-Leibler divergence are prone to mode collapse, while annealing-based methods, commonly using geometric schedules, can suffer from mass teleportation and rely heavily on schedule tuning. We introduce Constrained Mass Transport (CMT), a variational framework that generates intermediate distributions under constraints on both the KL divergence and the entropy decay between successive steps. These constraints enhance distributional overlap, mitigate mass teleportation, and counteract premature convergence. Across standard BG benchmarks and the here introduced ELIL tetrapeptide, the largest system studied to date without access to samples from molecular dynamics, CMT consistently surpasses state-of-the-art variational methods, achieving more than 2.5x higher effective sample size while avoiding mode collapse.

Distributed resource allocation (DRA) is fundamental to modern networked systems, spanning applications from economic dispatch in smart grids to CPU scheduling in data centers. Conventional DRA approaches require reliable communication, yet real-world networks frequently suffer from link failures, packet drops, and communication delays due to environmental conditions, network congestion, and security threats. We introduce a novel resilient DRA algorithm that addresses these critical challenges, and our main contributions are as follows: (1) guaranteed constraint feasibility at all times, ensuring resource-demand balance even during algorithm termination or network disruption; (2) robust convergence despite sector-bound nonlinearities at nodes/links, accommodating practical constraints like quantization and saturation; and (3) optimal performance under merely uniformly-connected networks, eliminating the need for continuous connectivity. Unlike existing approaches that require persistent network connectivity and provide only asymptotic feasibility, our graph-theoretic solution leverages network percolation theory to maintain performance during intermittent disconnections. This makes it particularly valuable for mobile multi-agent systems where nodes frequently move out of communication range. Theoretical analysis and simulations demonstrate that our algorithm converges to optimal solutions despite heterogeneous time delays and substantial link failures, significantly advancing the reliability of distributed resource allocation in practical network environments.

The integration of Unmanned Aerial Vehicles (UAVs) into Open Radio Access Networks (O-RAN) enhances communication in disaster management and Search and Rescue (SAR) operations by ensuring connectivity when infrastructure fails. However, SAR scenarios demand stringent security and low-latency communication, as delays or breaches can compromise mission success. While UAVs serve as mobile relays, they introduce challenges in energy consumption and resource management, necessitating intelligent allocation strategies. Existing UAV-assisted O-RAN approaches often overlook the joint optimization of security, latency, and energy efficiency in dynamic environments. This paper proposes a novel Reinforcement Learning (RL)-based framework for dynamic resource allocation in UAV relays, explicitly addressing these trade-offs. Our approach formulates an optimization problem that integrates security-aware resource allocation, latency minimization, and energy efficiency, which is solved using RL. Unlike heuristic or static methods, our framework adapts in real-time to network dynamics, ensuring robust communication. Simulations demonstrate superior performance compared to heuristic baselines, achieving enhanced security and energy efficiency while maintaining ultra-low latency in SAR scenarios.

Intelligent reflecting surface (IRS) assisted unmanned aerial vehicle (UAV) systems provide a new paradigm for reconfigurable and flexible wireless communications. To enable more energy efficient and spectrum efficient IRS assisted UAV wireless communications, this paper introduces a novel IRS-assisted UAV enabled spectrum sharing system with orthogonal frequency division multiplexing (OFDM). The goal is to maximize the energy efficiency (EE) of the secondary network by jointly optimizing the beamforming, subcarrier allocation, IRS phase shifts, and the UAV trajectory subject to practical transmit power and passive reflection constraints as well as UAV physical limitations. A physically grounded propulsion-energy model is adopted, with its tight upper bound used to form a tractable EE lower bound for the spectrum sharing system. To handle highly non convex, time coupled optimization problems with a mixed continuous and discrete policy space, we develop a deep reinforcement learning (DRL) approach based on the actor critic framework. Extended experiments show the significant EE improvement of the proposed DRL-based approach compared to several benchmark schemes, thus demonstrating the effectiveness and robustness of the proposed approach with mobility.