CORAL: An LLM-Native Harness for Production Recommender Systems

Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user behavior, and upstream models shift, the choices governing retrieval, ranking, and serving must be revisited. Traditionally, human engineers test such changes through online experiments--a slow, reactive process limited by engineering effort, leaving parts of the system unrevised as conditions change. Although large language models have been applied to ranking, user modeling, and offline model development, few systems place an agent in a continual closed loop that acts on a live recommender and learns from the measured effects of its decisions. We present CORAL (Constraint-Optimized Recommender via an Agentic Loop), an LLM-native harness that closes this loop: each cycle, the agent observes operating signals, reasons over a memory of past decisions and outcomes, and invokes tools--including a numerical optimizer that keeps changes within a fixed operating budget--to reconfigure the recommender, with measured outcomes informing the next cycle. We formulate this as a partially observed, non-stationary, constrained optimization problem in which the policy improves in context, without parameter updates, from its prior actions. Across two large-scale social platforms, evaluated with A/B experiments, the same harness improves engagement at no additional serving cost on one and reduces serving cost without degrading engagement on the other, spanning the engagement-efficiency frontier. Performance improves as the loop iterates, suggesting that a single agentic loop can automate continual optimization work traditionally performed by human algorithm engineers under explicit guardrails.

Denoising as Projection: Constrained Optimization with Gradient-Guided Diffusion

Diffusion models are increasingly used not only for sampling from learned data distributions, but also for generating samples that optimize task-specific objectives. A common approach is to guide the reverse diffusion process using gradients of an external objective. However, when the data distribution is supported on a structured feasible set, such as a manifold or a constraint set, gradient guidance can move samples away from the learned data geometry. In this paper, we study a simple projected-gradient-guided diffusion update based on the observation that the Stein denoising operator can act as an approximate projection onto the data geometry. The proposed update incorporates the objective gradient inside the denoising step, yielding an inference-time method that uses only a pretrained denoiser and gradient evaluations. We analyze this update as an inexact projected-gradient method for constrained optimization over learned feasible geometries. Our theory covers three settings: linear manifolds, compact convex feasible sets, and compact Riemannian submanifolds. In all these settings, we prove descent and finite-time convergence guarantees. Numerical experiments support the theoretical interpretation and illustrate how the proposed update balances objective descent with preservation of the learned geometry.

CG4AI: A Column Generation Framework for Training AI Models Under Constraints

Standard machine-learning training minimizes a loss function over a dataset, but does not guarantee that the resulting model will satisfy predefined rules or constraints on its outputs. In many real-world applications, ranging from autonomous systems to network routing, such guarantees are essential. We propose CG4AI, a framework that builds a convex combination of AI models while enforcing linear constraints on the combined output. A master linear program (LP) determines the optimal mixture weights, while a pricing subproblem generates new models guided by LP dual variables, focusing attention on the most violated constraints. A cutting-plane procedure extends feasibility guarantees beyond the training set. We apply CG4AI to two problems: (i) digit classification on MNIST, where we demonstrate four distinct uses of constraints, learning from constraints alone, improving adversarial robustness, correcting misclassified examples, and enforcing output relabeling; and (ii) the multi-commodity flow problem, where link capacity constraints are enforced on neural-network routing predictors. Experiments on MNIST and standard SNDLIB benchmark networks show that CG4AI reliably produces feasible predictors while achieving better accuracy than single-model baselines.

Primal--Dual Alternating Neural Learning for Timely Classification with Performance Guarantees

Timely risk classification is essential in many clinical monitoring settings, where decisions must balance the benefit of classifying patients early for subsequent intervention against the value of observing additional data. Yet most existing statistical and machine-learning methods are designed for fully observed trajectories and offer limited control over key operating characteristics such as sensitivity, specificity, and monitoring cost. We cast the sequential classification problem within a multi-objective optimization framework targeting these three criteria. We characterize the optimal decision rule through a value recursion that quantifies, at each time point, the trade-off between immediate classification and continued monitoring. To estimate the rule from data, we formulate a constrained optimization problem that maximizes specificity while enforcing prespecified sensitivity and monitoring-cost constraints. We then develop an estimation procedure that employs a recurrent neural network to approximate the evolving value processes and a primal--dual updating scheme to satisfy the performance constraints. Through simulation studies and an application to continuous glucose monitoring for hypoglycemia risk prediction, we demonstrate that the proposed method yields accurate and timely sequential decision rules that adhere to the desired operating characteristics.

Coverage-Maximizing Multinomial Subset Routing under Operational Constraints

We introduce Multinomial Subset Routing (MSR), a new online routing framework over $K$ experts in which the learner keeps a multinomial routing policy instead of a deterministic subset of experts. At each round, the learner samples $M$ experts i.i.d. from the multinomial policy, and the resulting set of distinct sampled experts forms the routed subset. The reward depends only on the best-performing expert(s) in the routed subset. This reward structure arises naturally in routing across specialized models but is not captured by standard combinatorial bandits or subset-selection methods, which optimize deterministic subsets and typically assume additive rewards. We require the selection to satisfy several long-term, two-sided operational constraints under bandit feedback, observing only the winner's reward each round. We propose OMD-Approachability, combining online mirror descent with Blackwell's Approachability, and prove it achieves $O(1/\sqrt{T})$ regret in both reward and constraint violation. We ground the framework in practical application domains and validate it empirically on a real-world crowdsourcing dataset.

BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice

Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic KYC-style constraints on risk, fees, and diversification. This is especially problematic in agentic multi-turn advisory systems, where each draft recommendation can become an action unless guarded by an auditable enforcement layer. We study a model-agnostic, asset-agnostic post-generation guardrail pipeline: (i) enforce a strict JSON allocation schema, (ii) validate allocations against numeric caps, and (iii) when violations occur, deterministically project the output to the nearest feasible portfolio via a convex quadratic program (QCQP). We introduce BiasMix-Finance (Mini), a compact stress-test benchmark for constrained decision-making under biased LLM generations, with a 16-ETF universe, three investor profiles, and eight bias prompts. Across three models and three inference modes (direct, critique, self-consistency), first-pass generations violate at least one cap in 47.6-85.7% of test cases (67.2% pooled), but the convex projection layer reduces final feasibility violations to 0% while requiring only a small correction distance (test pooled median D=||w*-w0||_2=0.066), indicating that the guardrail typically preserves the intent of the original allocation. We report violation rates and correction distances with confidence intervals, and paired model comparisons with multiple-testing correction. To support reproducibility, we release the dataset, prompts, caps, and code in our public GitHub repository.

Basin: Efficient and Extensible Numerical Optimization in Rust

Basin is a numerical optimization library for the Rust programming language. Numerical optimization is the task of finding the inputs that minimize a function, and it is a fundamental element across the sciences: fitting a model to data, calibrating a simulation, training a machine learning model, or choosing engineering parameters that minimize cost. Basin gives users a single, consistent way to both state and solve such problems, with a broad catalog of solvers and first-class support for constraints.

Safety Cost of Steering Vectors Is Separable and Reducible

Steering vectors are a lightweight tool for controlling LLM behavior. However, emerging evidence shows that steering vectors can unintentionally compromise a model's safety mechanisms and increase compliance with harmful requests, while no effective mitigation yet exists. In this work, we show that this safety degradation arises from a separable component in the vector that disrupts the model's safety mechanisms but contributes little to the steering objective. We identify and remove this safety-degrading component, formulating the task as a constrained optimization problem solved through primal-dual updates, subject to preserving the intended steering effect and bounding false refusal. The resulting solution is both interpretable and surgical: the optimization recovers a single direction whose ablation from the steering vector restores model safety with minimal utility cost. Across models, steering behaviors, and attack suites, including unseen attacks types, our method substantially reduces steering-induced safety degradation while preserving the original steering effect with minimal impact on false refusal. Our method offers a post-hoc correction to steering vectors that mitigates their safety cost, and more broadly, it provides a general recipe for applying activation-level model interventions without paying a safety tax.

Generative Optimization for Incentivized Advertising with Global Level Constraints

Incentivized advertising allocates monetary or virtual rewards to drive user engagement, where a key challenge is optimizing continuous incentive magnitudes under strict global constraints. This problem is complicated by high-frequency interactions, delayed feedback, and non-Markovian user dynamics such as fatigue, which limit the effectiveness of existing uplift modeling and constrained reinforcement learning approaches. To address these challenges, we propose GOAL, a constraint-aware generative framework that formulates incentive allocation as a conditional sequence generation problem. GOAL directly generates incentive magnitudes conditioned on user histories and system-level global pressure, and integrates a hierarchical causal state encoder to capture both local behavioral dynamics and long-range dependencies. To enable flexible constraint control, we introduce \textbf{S}afe \textbf{C}onstrained \textbf{P}olicy \textbf{O}ptimization (SCPO), which learns a single generative policy that generalizes across a spectrum of ROI constraints without retraining. Experiments on large-scale real-world data and a synthetic fatigue-aware environment show that GOAL improves long-term revenue and user retention while substantially reducing ROI violation rates compared to strong baselines.

Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection

Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constraints. Mixed-integer linear programs (MILPs) handle such constraints flexibly but scale poorly in stochastic environments. Deep reinforcement learning (DRL) promises scalable decision rules, but existing methods either penalize constraints rather than enforce them, or rely on feasibility mechanisms that break down once constraints interact. We bridge this gap by embedding a differentiable convex optimization module inside the policy: a neural network proposes continuous action targets, a quadratic program projects them onto the relaxed feasible set, and a dual-informed integer mapping restores integrality while preserving feasibility. Given a differentiable simulator, the policy trains end to end from sampled trajectories using pathwise gradients, while handling hard constraints with similar flexibility to MILPs. We show that our feasibility enforcement has bounded error relative to an exact integer projection and ensures the entire feasible action space is reachable. We apply the method to multi-echelon production-inventory planning under shared resource and material constraints. Our policy attains an average optimality gap below 1% on small instances. It further outperforms state-of-the-art echelon base-stock policies by up to 9.75% and a rolling-horizon multi-stage stochastic program by at least 7.7% in larger networks. On an industry-scale case study from ASML, it reduces average cost by up to 3.22% relative to the best-known benchmark policy. The savings are largest where planning is hardest: in tightly capacitated systems with high demand variability. More broadly, our work shows that DRL can deliver economically significant savings in sequential decision problems with interdependent hard constraints, which are widespread in practice.

Heterogeneous Multi-Agent Reinforcement Learning for Radio Resource Management under Coupled Finite-Horizon Constraints

Maximizing throughput under proportional fairness in dense wireless networks requires jointly managing user association, scheduling, base station (BS) activation, and handover control under hard finite-horizon energy and handover budgets, which induces a fundamental tension between BS-side energy management and user-side handover regulation. While multi-agent reinforcement learning (MARL) is a natural framework for such distributed sequential control, its application here faces two difficulties: finite-horizon budget constraints cannot be evaluated at each time slot, and the nonlinear proportional fairness utility admits no principled per-slot decomposition. We propose HeLyMARL, a Lyapunov-embedded heterogeneous MARL framework that resolves both via drift-plus-penalty decomposition with virtual queues. The energy and handover constraint pressures are internalized directly into a unified per-slot reward, converting the constrained finite-horizon problem into an unconstrained MARL problem. Comparison against two Lagrangian-based alternatives reveals a timescale separation: Lagrangian relaxation regulates constraints only across training episodes, whereas the virtual queues of HeLyMARL bound cumulative budget consumption at every partial horizon within an episode, a pacing guarantee beyond the reach of greedy Lyapunov-based control. Simulations show that HeLyMARL is the only method that sustains the throughput-fairness balance together with uninterrupted service throughout the horizon, outperforming conventional MARL, Lyapunov-based, and constrained MARL benchmarks without premature budget exhaustion.

Optimization with Dynamic Constraint Learning (DCL)

We propose Dynamic Constraint Learning (DCL), a data-driven framework for constrained optimization when constraint functions are unknown and cannot be queried during optimization. At each iteration, the method learns a local surrogate from nearby data and solves a subproblem within a data-supported trust region. Compared with offline global constraint learning, the approach uses local surrogates that adapt to the data distribution during optimization and can achieve solution quality comparable to that of global models while using simpler local models and smaller optimization subproblems. We demonstrate the performance of DCL on a synthetic test problem and two case studies from the literature.

A Multi-stage Constrained Optimization Framework for Data-driven Problems

Variational autoencoders (VAEs) transform high-dimensional, often noisy data into a compact latent representation, making downstream optimization more tractable. Three challenges persist in VAE-based constrained optimization: (i) sampling effectively within the latent space, (ii) identifying the active decision variables that actually influence the objective and constraints, and (iii) enforcing constraints without destabilizing training. We propose a Multi-stage Constrained Optimization Framework (MCOF). First, an entropy-constrained VAE (EC-VAE) coupled with a feature selector embeds objective and constraint information into a designated subset of latent variables, so that optimization proceeds over a low-dimensional subspace while the remaining coordinates supply solution diversity. Second, a Uniform Transformation (UT) module applies a per-dimension probability integral transform, replacing the irregular aggregate posterior with a uniform distribution over a bounded box and mitigating posterior collapse and Gaussian mixture bias. Third, a constraint-priority filter method (CPFM) solves the resulting surrogate problem by alternating violation-reduction and objective-reduction steps under a filter acceptance test, returning solutions that are feasible for the learned surrogate to a specified tolerance without requiring multiplier estimation. Finally, unselected latent coordinates are resampled to generate diverse decodings of a single optimized solution. We validate MCOF on a synthetic problem, where we ablate each stage and recover the analytic optimum, and on a ZINC250k drug design task, where the generated molecules satisfy the imposed constraints and are entirely novel relative to the training set.

Constraint-Bound Agnostic Bayesian Optimization: One Model for All Thresholds

Expensive constrained optimization problems in real-world industry design often involve constraint thresholds that are difficult to determine in advance. Engineers may need to adjust constraint thresholds to explore different feasibility-performance trade-offs, requiring solutions under a wide range of threshold settings. However, existing constrained Bayesian optimization methods treat each threshold configuration independently, leading to repeated optimization and failing to exploit the shared relationship among continuously varying thresholds. To address this challenge, we propose constraint-bound agnostic Bayesian optimization (CBA-BO), a learning-based framework that learns a parametric constraint model mapping thresholds to optimal solutions. Once learned, CBA-BO directly predicts solutions for arbitrary unseen threshold configurations without additional optimization, with a one-step Bayesian optimization refinement further improving solution quality. Experiments on benchmark and engineering problems demonstrate that CBA-BO learns a transferable threshold-solution mapping, enabling efficient prediction and optimization for arbitrary threshold queries. An intent-guided constraint-bound recommendation mechanism is further developed to improve objective performance while satisfying user-specified constraint preferences.

Agentic Calibration of Grey-Box Simulation Models: An LLM-Driven Alternative

Calibration of grey-box simulation models is a constrained optimization problem in which model evaluations are expensive, the parameter space can be high-dimensional, and the search must respect plausibility constraints. Although the simulation code is fully available to the analyst, the joint effect of multiple parameters remains difficult to predict analytically. Classical optimizers such as Nelder--Mead (NM) are simple to deploy but sample-inefficient, particularly under constraints. Modern Bayesian Optimization methods achieve competitive solutions with far fewer evaluations but require non-trivial modeling machinery for constraint handling. We introduce an agentic calibration method in which a large language model acts as the optimizer, with constraints incorporated as a plain-language section of the system prompt. We evaluate the agentic method, NM, and Bayesian Optimization (BO) on an anal cancer simulation model under both unconstrained and clinically constrained calibration. Under unconstrained calibration, the agentic method achieves substantially lower best error than BO and NM, while requiring fewer model evaluations. Under constrained calibration, the agentic method reaches comparable error levels and both outperform NM. These results are obtained at the cost of increased inference time per iteration. Agentic calibration achieves competitive performance with substantially fewer model evaluations, and constraint handling is essentially free at the modeller-facing interface through simple textual specifications rather than additional modelling machinery. The main trade-off lies in increased per-iteration inference cost, making the approach particularly suitable when simulation time dominates. Beyond performance, the per-iteration rationale makes the search auditable and explainable, so its decisions can be scrutinised and justified to third parties.

Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization

We introduce a constrained two-view framework for node prediction that aligns structure-conditioned GNN embeddings with a structure-free feature prior learned by an anchor model. Conventional Graph Neural Networks (GNNs) couple feature transformation and neighborhood aggregation, which renders them vulnerable to topology noise and heterophilous connections. To decouple this dependency, our framework utilizes an independent anchor network to capture intrinsic attribute features via a self-supervised reconstruction objective. Furthermore, we propose a Channel-Split Adaptive Gated GNN (CSAG-GNN) that dynamically routes representations between global spectral smoothing and local spatial discrimination through a node-wise gating mechanism. We propose a stable cyclic alternating optimization strategy to solve the resulting coupled bi-level objective, preventing mutual representation drift during training. Empirical results on both homophilous and heterophilous benchmarks show balanced performance gains and structural robustness over competitive baselines.

Constrained Bayesian Optimisation with Multiple Information Sources

Bayesian Optimisation (BO) under unknown constraints is particularly challenging when feasible regions are small. In such settings, existing methods that typically rely solely on evaluations of the true objective and constraints struggle to efficiently explore the design space. However, many real-world applications offer auxiliary data sources (e.g. surrogate models or simplified simulations) that can support early exploration. Despite this potential, their integration into constrained BO remains largely unexplored. We propose a general multi-source framework that extends constrained Max-value Entropy Search, capturing inter-source correlation while balancing evaluation cost and information gain. Experiments on both synthetic and physics-based benchmarks show that our method efficiently identifies feasible and optimal solutions, even when auxiliary data are only weakly correlated. The proposed approach consistently outperforms existing methods, particularly in early-stage exploration.

PoseShield: Neural Collision Fields for Human Self-Collision Resolution

Self-collision remains a persistent challenge in SMPL-based human pose estimation and motion generation. Under extreme articulations or stochastic motion synthesis, generated meshes frequently exhibit self-penetrations, leading to physically implausible results. We propose PoseShield, a neural collision constraint defined directly in SMPL pose space. We formulate collision correction as a constrained optimization problem and connect the learned constraint with the Eikonal equation. Enforcing Eikonal regularization ensures non-vanishing gradients near the collision boundary, improving numerical stability and robustness of the optimization process. Unlike prior methods that operate in the mesh space or rely on heuristic penalties, our approach operates directly in the low-dimensional space of human poses and is theoretically grounded. The same learned constraint extends to human motion sequences, providing a generator-agnostic post-hoc collision corrector without retraining the underlying motion model. Experiments on a newly constructed SMPL pose benchmark show that our method achieves a 95.8% success rate and outperforms state-of-the-art baselines.

A Multi-Agent system for Multi-Objective constrained optimization

Many decision-making problems in computing and networking systems can be naturally formulated as cost-minimization problems under performance constraints. In dynamic environments, reinforcement learning (RL) is often used to solve such problems at runtime by embedding both costs and constraint violations into a single scalar reward through weighted penalty terms, following a Lagrangian-inspired formulation. However, in this context the behavior of the learned policy critically depends on the choice of these weights, which are typically selected manually. This makes it difficult to identify an appropriate trade-off between optimizing the primary objective and effectively avoiding constraint violations, particularly in non-stationary environments where their relative importance may change. This paper presents MAMO (Multi-Agent system for Multi-Objective constrained optimization), an approach to tackle this balancing problem through multi-agent RL. MAMO decouples task execution from objective design by formulating the selection of reward weights as a learning problem, providing a !rst step towards more autonomous and robust RL-based solutions for constrained optimization problems in dynamic environments.

A Human-in-the-Loop Bayesian Optimization Framework for Constraint-Aware Bioprocess Development

This work presents an extension to Pareto Front Guided Sampling (PFGS), a Human-in-the-Loop (HitL) Bayesian Optimization (BO) framework in which Gaussian process (GP) surrogate-derived quantities are reformulated as objectives of a multi-objective optimization problem, and the resulting Pareto front is exposed to a domain expert for interactive candidate selection rather than returning a single automated recommendation. The framework is extended in two directions: constrained optimization is addressed by incorporating the posterior probability of satisfying output specification limits as an explicit Pareto objective, computed analytically from the GP posterior distribution; robust optimization is addressed by a Monte Carlo sampling strategy that estimates expected lower-confidence performance over a user-defined variability of input perturbations, capturing performance degradation under likely implementation deviations. The resulting multi-dimensional Pareto representation renders trade-offs between predicted performance, model uncertainty, probabilistic constraint satisfaction, and input robustness simultaneously visible through pairwise two-dimensional projections on an interactive dashboard, enabling selection criteria to be iteratively refined as the surrogate model improves and development objectives evolve. The framework is showcased on an eight-dimensional fed-batch Chinese Hamster Ovary (CHO) cell culture simulator demonstrating systematic identification of high-performing, feasibility-compliant, and perturbation-resilient operating conditions, and illustrating how expert-defined requirements provide a principled stopping criterion and support informed allocation of experimental resources.

TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning

Safe coordination in networked cyber-physical systems forces learning algorithms to simultaneously handle hybrid discrete-continuous actions, hard training-time safety constraints, and physics-governed dynamics. We show that these three features form a directed cycle of biases that defeats any naive composition of off-the-shelf modules, and formalize this as a three-way coupling lemma. We then introduce TRIDENT, the first MARL framework whose three components are co-designed to cancel each leak: a Richardson-Romberg gradient correction reducing Gumbel-Softmax bias from O(tau) to O(tau^2), a Lyapunov-constrained sequential trust-region update enforcing per-iterate feasibility, and a physics-informed residual critic that decomposes value rather than reward. We prove an O~(1/sqrt(K)) convergence rate to a constrained Nash equilibrium and an O(sqrt(K)) cumulative-violation bound. On multi-UAV mobile-edge computing, autonomous intersection management, and a hybrid SMAC variant, TRIDENT cuts training-time violations by 95.5% over MADDPG and 76.3% over MACPO, while improving reward by 13.5% over the strongest unconstrained baseline.

p-PSO: A Penalized Particle Swarm Optimization Technique for Finding D-Optimal Designs with Mixed Factors in Generalized Linear Models

Finding D-optimal designs for generalized linear models (GLMs) is challenging due to the dependence of the Fisher information matrix on unknown parameters and the lack of closed-form solutions, particularly when input factors include both discrete and continuous variables. Although classical algorithms and recent metaheuristic approaches have offered partial solutions, there remains a need for robust and computationally efficient methods. In this paper, we propose a penalized Particle Swarm Optimization (PSO) approach, named $p$-PSO. Here we introduce a new, general-purpose penalty formulation for constrained optimization and demonstrate its effectiveness in optimal design problems. The formulation is algorithm-agnostic and applicable to a broad class of black-box optimization methods. Results show that the method is highly efficient, with its primary contribution being a penalty formulation that enables the direct use of an off-the-shelf PSO algorithm and extends naturally to more general constrained optimization tasks.

Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response

Autonomous network-security response systems promise to reduce Security Operations Centre (SOC) reaction latency, but reward-only multi-agent reinforcement learning (MARL) can improve security reward while remaining non-deployable. We present a safety-contract graph MARL framework and instantiate it as ACD$^3$-GAT (Adaptive Constrained Counterfactual Decisioning with a Graph Attention Network encoder), an architecture that separates simulator observations from reusable operational budgets, constrained optimization, graph state encoding, and counterfactual action screening. We evaluate the method in CAGE Challenge 4, where agents operate under budgets for Mean Time to Recover (MTTR), false-positive response, and firewall change-management disruption. Across the benchmark, every unconstrained method violates the SOC downtime budget in 100% of evaluated episodes, with mean downtime proxy costs of 311-430 against a budget of 50. This complements prior CAGE Challenge 4 findings by showing that reward-only learning lacks operational discipline. Constrained MAPPO-GAT (C-MAPPO-GAT) isolates Lagrangian operational-cost control and budget-aware screening, while ACD$^3$-GAT adds budget context, CVaR tail-risk estimation, opponent-belief state, and Graph Counterfactual Risk Propagation (G-CRP). The replicated comparison includes three 200-episode seeds for IPPO, MAPPO-GAT, C-MAPPO-GAT, and ACD$^3$-GAT. C-MAPPO-GAT reduces downtime violation from 100% to 0.3% and mean downtime cost from 355.4 to 15.5 relative to MAPPO-GAT. ACD$^3$-GAT reduces mean downtime cost to 48.2 with a 13.8% violation rate, placing it on the safety-contract frontier rather than at the most conservative compliance point. Topology-seed and coupled adaptive Red-process stress tests preserve this contrast and show lower worst adaptive degradation for safety-constrained policies than reward-only MAPPO-GAT.

Neural Slack Variables for Shape Constraints

Enforcing functional inequality constraints such as monotonicity and convexity in neural networks is a fundamental challenge in many industrial and scientific applications. Classical one-sided penalty methods, along with primal-dual methods gated by complementary slackness, provide constraint gradients only at violated locations, resulting in fragile satisfaction. Architectures that guarantee feasibility by construction, on the other hand, remain largely limited to elementary cases and impose additional inductive biases. We introduce neural slack variables, a deep learning native primal-side approach that converts constraint enforcement into a regression problem by coupling the primary network with a jointly learned auxiliary network. The auxiliary network serves as a valid target for the primary network's constraint quantities, inducing feasibility and regularity. Neural slack variables achieve zero measured violations on dense-grid monotonicity and convexity test cases, where penalty and primal-dual baselines leave residual violations, and enable arbitrage-free learning of volatility surfaces, an open industrial challenge in quantitative finance.

Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents

Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts that exceed their finite context windows, making memory retention a fundamental resource-allocation problem. Existing memory systems improve management through heuristic scoring, retrieval optimization, or learned compression, but largely treat retention as a local decision problem and do not explicitly model its long-term consequences under realistic observability constraints. To fill this gap, we formulate memory retention as a constrained stochastic optimization problem with explicit budget feasibility, evidence utility, and delayed costs including miss penalties, reacquisition delays, and stale-information risk. We then propose OSL-MR (Observability-Safe Learning for Memory Retention), a novel framework that enforces a strict separation between online-observable features and offline-available supervision (OAS). OSL-MR combines an evidence learner trained from realized evidence supervision with a Mixed-Score heuristic that serves both as a deployable online-safe baseline and as a structured inductive prior for learning. The resulting policy learns query-conditioned evidence value directly from interaction data while remaining deployable under the same observability constraints. Experiments on LOCOMO and LongMemEval show that OSL-MR consistently outperforms recency-based methods, Generative Agents-style scoring, and other heuristic baselines, particularly under tight memory budgets. The Mixed-Score prior further improves precision while preserving recall, and sensitivity analysis demonstrates robustness across a wide range of cost configurations.

Constrained Paraphrase Consistency for LLM Hallucination Detection

Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors. Prior work largely enlarges training sets via synthesis or new annotations, introducing increasing cost and potential bias while underusing the consistency implied by semantically equivalent paraphrases. We propose Consistency-Constrained Hallucination Detector (CCHD), which formulates training as a constrained optimization problem. The standard cross-entropy on original document-claim pairs is complemented by (i) paraphrase-consistency constraints bounding divergence across paraphrased views, and (ii) label-preservation constraints tying paraphrases to ground truth. We solve the problem by gradient descent-ascent over model parameters and per-view Lagrange multipliers, adding only a few scalar dual variables and no inference-time overhead. With DeBERTa and Flan-T5 backbones, CCHD consistently outperforms strong baselines (FactCG, MiniCheck, and AlignScore) on standard factuality benchmarks, demonstrating its superiority on hallucination detection.

Noise-Adaptive High-Probability Regret Bounds for Online Convex Optimization

We study high-probability regret bounds for online convex optimization (OCO) with strongly convex losses and establish three results that resolve open questions at the intersection of noise adaptivity, feedback structure, and constraint satisfaction. For the full-information setting with sub-Gaussian stochastic gradients, we prove a noise-adaptive high-probability regret bound in which the martingale deviation term scales with the noise level $σ$ rather than the gradient bound $G$, yielding a multiplicative improvement of $G/σ$ over the classical Azuma-Hoeffding baseline. Our analysis introduces an exponential supermartingale argument that bypasses the bounded-difference requirement of Freedman's inequality, enabling direct treatment of unbounded sub-Gaussian noise without truncation artifacts. For bandit feedback, we prove a minimax lower bound: the high-probability regret scales linearly in $\log(1/δ)$, in contrast to the $\sqrt{\log(1/δ)}$ confidence cost under full information. This constitutes a formal separation in the confidence cost of strongly convex OCO across feedback models. Regarding constrained OCO with stochastic constraints satisfying a Slater condition, we provide simultaneous high-probability guarantees for both cumulative regret and long-run constraint violation, achieving $\mathcal{O}(\sqrt{T\log(m/δ)})$ regret and $\mathcal{O}(\sqrt{T}/(ζδ) + m\sqrt{T\log(m/δ)})$ violation. Synthetic experiments corroborate all theoretical predictions.

Residual-Controlled Multiplier Learning for Stochastic Constrained Decision-Making

Stochastic constrained decision-making requires optimizing performance objectives while enforcing statistical requirements such as safety or fairness. However, standard primal--dual methods struggle to update multipliers robustly under stochastic mini-batch feedback, as the noise of mini-batch gradients and constraint estimates can be directly accumulated into the multiplier memory. To address this issue, we propose Residual-Controlled Multiplier Learning (RCML), which reformulates multiplier updating as projected-pressure feedback. The central idea is to decompose the projected multiplier into an effective pressure signal for primal descent and a pressure-memory residual for finite-gain multiplier tracking. To handle heterogeneous and noisy observations, we further augment this residual-integral backbone with modular stochastic stabilization components. For the convex-affine backbone, we establish finite-gain convergence, derive a stochastic residual bound under mini-batch feedback, and show that the residual feedback law admits a local KKT-residual interpretation near regular KKT points of nonconvex problems. Experiments across optimization, allocation, and fair-ranking tasks show that RCML improves feasibility control and multiplier stability while maintaining competitive objective performance. Code is released at https://anonymous.4open.science/r/RCML-3114/.

Multi-ResNets for Subspace Preconditioning in Constrained Optimization

We propose MResOpt, a staged residual neural network architecture for constrained optimization problems. Our architecture fits within predict-complete-correct pipelines and decomposes constraint satisfaction by priority through intermediate re-completion and stage-aware losses. The framework enables domain-informed ordered constraint satisfaction which allows the network to utilize ordinal structure when present. Under an idealized infinite-width regime, we show that our design behaves as sequential Gaussian Process regression. On synthetic QP, QCQP, and SOCP benchmarks, the staged architecture improves high-priority constraint satisfaction across convex and non-convex settings. On line-flow-constrained AC optimal power flow, we introduce a physics-motivated constraint ordering and show that MResOpt supports a learned division of labor that keeps iterates on the equality manifold, achieving substantially lower high-priority violation than reprojected baselines while remaining computationally efficient.

DiffSlack: Learning under Nonlinear Inequality Constraints via Learnable Slack Variables

Enforcing nonlinear inequality constraints in neural networks remains challenging, especially when the output is subject to many coupled constraints. Existing hard constraint methods often impose structural restrictions on the constraint set or introduce substantial computational overhead for large-scale nonlinear problems. Here, we propose DiffSlack, a differentiable projection layer for nonlinear inequality-constrained neural prediction. DiffSlack reformulates inequalities as equalities with learnable slack variables, which are predicted as part of the augmented network output and provide a data-driven warm start for damped Gauss-Newton projection. The projection layer maps raw predictions onto the augmented feasible manifold while preserving end-to-end differentiability. A two-stage curriculum further stabilizes training and improves constraint satisfaction. We evaluate DiffSlack on vehicle path planning with 200 nonlinear inequality constraints from collision avoidance, curvature limits, and waypoint spacing. Compared with existing learning-based baselines, DiffSlack achieves a higher planning success rate and stronger geometric constraint satisfaction under a comparable inference budget. Ablation studies further show that the hard projection layer reduces sensitivity to supervision quality. Closed-loop tracking in CARLA and real-world vehicle experiments confirms the executability of the generated trajectories. These results demonstrate that DiffSlack provides a practical and scalable approach to embedding hard inequality constraints into neural networks for engineering applications.