Constructing Streams of Optimization Instances for Benchmarking Algorithm Selection and Configuration Approaches in Streaming Scenarios

Sustainable Benchmarking Tool

Enhancing the Kubernetes Scheduler: A State-of-the-Art Review from Cloud to Edge

A comprehensive review of Kubernetes scheduling strategies published between January 2023 and January 2026 is presented and a multi-dimensional taxonomy is established that categorizes scheduling approaches based on common objectives, modification methods, optimization methodologies, targeted workloads, evaluation methods, scheduling scopes, and performance metrics.

Tuning Strategies for Heterogeneous Instance Sets Using irace

An extension of the irace framework, h-irace, is proposed that incorporates concurrent racing processes over predefined instance subsets that supports configuration specialization across heterogeneous instance subsets in both continuous and combinatorial optimization problems.

ClusterBench: A Framework for Cluster-Wide Continuous Benchmarking and Regression Testing

Data centers need tooling that validates an entire installation rather than individual nodes, at acceptance and at regular intervals thereafter. This requires dispatching identical benchmarks to every node in a single submission, and therefore cluster-aware scheduling. This paper presents ClusterBench, a framework for cluster-wide continuous benchmarking. It ships with a benchmark collection targeting each component: CPU, GPU, memory, interconnect, and I/O. Because measurements are repeated throughout the cluster's lifetime, ClusterBench collects data across space and time. Comparison against earlier runs detects performance regressions introduced by software changes, such as kernel updates or new library versions. The measurements also form a dataset for research on hardware variability. On the NHR@FAU clusters Helma, Alex, and Fritz, variation within a single component stays within 1%. Variation across specimens reaches 5%, despite nodes identical by specification. Correlating performance with power draw, frequency, and temperature shows that this relationship differs between air- and liquid-cooled nodes.

s2mflow: A meta-generator for multicommodity flow instances

Benchmark instances for multicommodity flow problems often fail to capture the structural characteristics of real-world networks or preserve a rigorous relationship with their single-commodity counterparts. To address these limitations, this paper presents s2mflow : an open-source, cross-platform Python library for lifting single-commodity minimum-cost flow instances into the multicommodity space. Unlike existing generators, s2mflow makes this structural relationship an explicit design principle of the instance construction process, enabling the generation of structurally grounded benchmarks. The package combines a Python interface with a high-performance Rust backend built with PyO3 and maturin, and is distributed via PyPI for Linux and macOS on x86_64 and ARM64, and Windows on x64. It provides integer partitioning methods to control commodity-demand heterogeneity, a key factor for the Single-Multi-Commodity Gap and solver performance. Additionally, s2mflow introduces the specialized .mcfmin file format for compact, reproducible storage. The resulting instances are suitable for benchmarking methods in linear programming, network optimization, and transportation science.

AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds

Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is insufficient in real-world decision settings such as route planning and fleet dispatch. Individual choices interact through shared constraints and costs, so a feasible solution may still be substantially suboptimal. This raises a harder question: can an agent turn information gathered through tools into a globally optimal decision? We introduce AlgoWorlds, a benchmark that transforms formally specified combinatorial optimization problems into partially observed decision environments with verifiable global optima. Each environment contains a hidden instance observed only through task-specific information tools, after which the agent commits to one structured decision evaluated for feasibility and optimality. AlgoWorlds contains 240 environments covering ten combinatorial optimization families and four workload levels. Family-specific deterministic programs generate the instances, exact algorithms certify their optima and determine workload levels, and two structurally different tool interfaces present each underlying instance. We evaluate seven leading LLMs, including Claude Opus 4.8 and GPT-5.6 Sol. Achieving global optimality remains highly challenging: although leading models produce feasible decisions in most cases, the best-performing model reaches exact optimality in only 38.61% of cases. Even when agents collect sufficient information to reconstruct the hidden instance, most failures end in feasible but suboptimal decisions. The challenge therefore extends beyond information acquisition to information integration, global constraint reasoning, and decision verification. The project homepage is available at https://xzx34.github.io/AlgoWorlds/, and the code is available at https://github.com/xzx34/AlgoWorlds.