22 articles tagged with #algorithm-design. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers used large language models and evolutionary search to create the first domain-independent heuristics for symbolic AI planning that surpass hand-engineered baselines. These evolved heuristics, written in C++, solve more planning tasks than existing state-of-the-art approaches and maintain the soundness guarantees of traditional planners.
Researchers have developed Glia, an AI architecture using large language models in a multi-agent workflow to autonomously design computer systems mechanisms. The system generates interpretable designs for distributed GPU clusters that match human expert performance while providing novel insights into workload behavior.
Researchers introduce BehaveSim, a new method to measure algorithmic similarity by analyzing problem-solving behavior rather than code syntax. The approach enhances AI-driven algorithm design frameworks and enables systematic analysis of AI-generated algorithms through behavioral clustering.
Researchers present a unified mathematical framework for gradient aggregation in multi-objective optimization (MOO), establishing convergence guarantees to Pareto stationarity. The work reveals that non-conflicting gradient directions within the convex hull satisfy sufficient conditions for convergence, enabling broader algorithmic approaches including a new method called capped MGDA for federated learning applications.
Researchers introduce simplified and factored cellular Weisfeiler Leman tests alongside maximal clique complexes to enable scalable higher-order graph neural networks. The CliqueWalk algorithm samples maximal cliques efficiently without explicit enumeration, addressing the critical scalability bottleneck that has limited adoption of topological learning approaches in production systems.
Researchers propose a novel framework for understanding equilibrium computation in games by mapping the geometric structure of game spaces to solver effectiveness. Rather than studying algorithms in isolation, they develop a learned representation that identifies which solver mechanisms work best across different game regimes, revealing continuous regions of algorithmic validity and suggesting that solvability is governed by underlying structural properties.
Researchers present optimal algorithms for sparse contextual bandits that achieve sample complexity of Õ((s/ε² + |A|/ε)log|Π|/δ), closing a gap from prior work that had exponential dependence on action set size. The results apply to multiclass classification and combinatorial semi-bandits through information-theoretic and algorithmic approaches.
Researchers demonstrate how selection hyper-heuristics can automatically adjust learning periods to optimize pseudo-Boolean problem solving, eliminating manual parameter tuning. The Random Gradient hyper-heuristic achieves optimal neighbourhood size selection in nearly all iterations while maintaining theoretically optimal performance on the LeadingOnes benchmark.
This academic paper advances Bayesian multiobjective optimization by clarifying how preference transformations affect two key performance indicators—hypervolume and R2—used in algorithm design. The research provides exact computational methods and proves that R2 improvement, contrary to prior assumptions, cannot be directly computed as objective-space hypervolume but instead represents volume in scalarization space, enabling new algorithmic implementations.
Researchers introduced FrontierOR, a benchmark that tests whether leading LLMs can design efficient optimization algorithms for real-world large-scale problems. The evaluation of seven models reveals significant limitations: even frontier models outperform Gurobi (a standard solver) in only 31% of cases, highlighting a substantial gap between LLM capabilities in formulation and practical algorithmic optimization.
LLM4Branch introduces a novel framework using large language models to automatically discover efficient branching policies for Mixed Integer Linear Programming (MILP) solvers. The approach generates executable programs via LLMs and optimizes parameters through performance feedback, achieving competitive results with state-of-the-art GPU-based methods on standard benchmarks.
Researchers propose a budget-efficient automatic algorithm design framework using large language models that operates on code graphs rather than full algorithms. The approach uses LLMs to generate compact corrections—code modifications that add, replace, or remove blocks—which compose into new algorithms, reducing computational waste and improving fitness outcomes on combinatorial optimization problems.
Researchers propose a marginalized reparameterization (MRP) estimator to enable practical use of mixture policies in reinforcement learning, addressing a long-standing gap between theoretical potential and practical implementation. By reducing variance compared to likelihood-ratio methods, MRP mixture policies achieve performance parity with standard Gaussian policies while offering greater flexibility in continuous action spaces.
A comprehensive arXiv survey examines the evolution of optimization algorithms for large language model training, moving beyond Adam toward memory-efficient, second-order, and matrix-based approaches. The research emphasizes that modern LLM optimization requires rigorous, scale-aware benchmarking that evaluates convergence, stability, memory usage, and implementation complexity rather than isolated speedup claims.
Researchers present new algorithms for efficiently selecting small, high-performing ensembles of AI systems using minimal model evaluations. The work addresses both binary feedback (correct/incorrect outcomes) and pairwise feedback (preference comparisons), providing theoretical guarantees and practical query-saving methods validated through LLM experiments.
Researchers introduce the Online Shared Supply Allocation (OSSA) problem, a theoretical framework for allocating limited resources across multiple locations before demand is known, common in humanitarian logistics and vaccine distribution. The proposed GPA algorithm achieves a 4/3-approximation ratio to optimal offline solutions, with proven tight bounds and a learning-augmented variant that incorporates forecasts.
Researchers introduce HMACE, a multi-agent AI framework that uses specialized language model agents to design heuristics for combinatorial optimization problems. The system achieves competitive results on benchmark problems while using significantly fewer computational tokens than existing methods, demonstrating improved efficiency in automated algorithm design.
Researchers demonstrate that Group Relative Policy Optimization (GRPO), traditionally viewed as an on-policy reinforcement learning algorithm, can be reinterpreted as an off-policy algorithm through first-principles analysis. This theoretical breakthrough provides new insights for optimizing reinforcement learning applications in large language models and offers principled approaches for off-policy RL algorithm design.
AlphaEvolve is a new AI coding agent powered by Gemini that can design and evolve advanced algorithms for mathematical and practical computing applications. The system combines the creative capabilities of large language models with automated evaluation systems to improve algorithm development.
Researchers present RDEx-CASK, an enhanced optimization algorithm that extends RDEx-CSOP with three modifications targeting stagnation issues in constrained single-objective optimization. The method introduces Cauchy-sampled scale factors, a small feasible-only archive, and per-individual stagnation counters that trigger adaptive parameter adjustments, achieving competitive performance on CEC benchmark problems.
Researchers have introduced LLM4AD, a unified Python platform that leverages large language models for algorithm design across optimization, machine learning, and scientific discovery domains. The platform features modular components, comprehensive evaluation tools, and extensive support resources including tutorials and a graphical user interface to facilitate LLM-assisted algorithm development.
This article explores a critical failure mode in reinforcement learning where algorithms break due to misspecified reward functions. The post examines how improper reward design can lead to unexpected and counterintuitive behaviors in AI systems.
