constrained-optimization

This paper formulates LLM reasoning distillation as a constrained reinforcement learning problem, maximizing task reward subject to a worst-case teacher-likelihood constraint along every step of the reasoning trajectory, avoiding the reward hacking of pure GRPO and the diluted task performance of KL-based distillation. Experiments on math reasoning and code generation show the method significantly expands the accuracy-fidelity Pareto front.

HARDEN introduces a constrained evolutionary search to generate more challenging evaluation cases for language models while preserving expected outputs, demonstrating significant accuracy reductions across benchmarks.

The paper proposes a deep architecture that jointly optimizes cost functions and route-ranking models for customizable route planning using differentiable shortest-path search, demonstrating significant improvements over state-of-the-art methods on real-world datasets.

LABELSENSE-Pilot is a reproducible prototype for point-feature label placement on interactive maps, using graph-context scoring and constrained optimization to balance geometric validity, stability, and accessibility. Experiments show it reduces flicker and maintains high display rates with zero collisions under various stressors.

This paper introduces a framework that decomposes compound logical answer options into atomic judgments and uses an operator-constrained integer linear program to improve large language model reasoning over AND, OR, and NEITHER/NOR operators. It achieves significant F1 gains on LOGICAL-COMMONSENSEQA and a new benchmark LOGICAL-SATA.

This paper introduces the Human Utility Factor (HUF), a computable welfare metric that reframes AI governance as a constrained optimisation problem with measurable levers for automation depth, redistribution, and employment coverage, validated through multi-agent simulations.

EXHOLD is a two-stage framework for real-time hold control in large-scale ride-hailing matching, improving passenger-driver experience and marketplace efficiency. Deployed in DiDi's Brazil market, it uses experience-aware pair assessment and constrained optimization to reduce cancellations and increase trip completion.

Proposes LARA, a framework for safe inference-time alignment that uses Lagrangian dualization to derive an augmented reward from separate reward and cost models, improving the helpfulness-harmlessness tradeoff without retraining.

The article describes an experiment using Claude Code to autonomously develop a file compression algorithm with constrained optimization, evaluating the viability of AI agents for unsupervised problem-solving.

PoseShield introduces neural collision constraints in SMPL pose space to resolve self-collisions in human pose estimation, achieving a 95.8% success rate on a new benchmark.

A blog post discussing optimization techniques for constrained categorical probability distributions, using softmax reparameterization and log barrier methods, applied to protein binder design.

Presents output vector editing, a constrained-optimization weight edit to mitigate memorization in LLMs by modifying MLP neuron output vectors instead of zeroing activations, achieving up to 87.9% suppression with minimal locality failures.

PSyGenTAB is a privacy-preserving framework that uses constrained optimization to generate synthetic clinical tabular data, balancing privacy and utility while preserving clinical relationships and minority-class patterns.

This paper proposes a constrained stochastic bandit algorithm for online selection of large language models under time-varying task demand and heterogeneous accuracy, latency, and cost profiles, with theoretical guarantees on regret and constraint violations.

This paper demonstrates that Optuna's constrained Tree-Structured Parzen Estimator (TPE) is a joint density generalization of the c-TPE algorithm, showing its invariance to constraint duplication while independent c-TPE degrades. The authors outline practical tradeoffs and directions for future study.

This paper formulates memory retention for long-horizon language agents as a constrained stochastic optimization problem, introducing OSL-MR, a framework that enforces observability-safe learning with a Mixed-Score heuristic. Experiments show consistent improvements over existing heuristic baselines under tight memory budgets.

Proposes CVT-RL, a constrained policy-gradient algorithm with policy-conditioned counterfactual contribution estimation and verifiable rewards, improving long-horizon language agent reliability and reducing reward hacking.

This paper formulates LLM inference budget allocation as a constrained optimization problem, proposing CLEAR to reallocate resources from low-utility queries to those near emergence thresholds, achieving up to 3× accuracy improvement under tight budgets.

Introduces Constrained Flow Optimization (CFO), a framework for fine-tuning generative flow models to maximize rewards while satisfying constraints in molecular design, with theoretical guarantees and experimental validation.

This paper presents a distributed approach for constrained multi-agent reinforcement learning that uses state-augmented policy learning and neighbor-to-neighbor consensus over dual variables to satisfy global resource constraints while scaling linearly with the number of agents. Experiments on smart grid demand response demonstrate that consensus coordination is essential for feasibility, scaling to thousands of agents unlike centralized training approaches.