arXiv AI October 19, 2026 By Jamie Fravel, Martin Kouteck\'y, Pavlo Tsitsei

Hard Instances on Demand

The paper presents a method for generating hard problem instances by treating instance creation as an optimization problem, using solver runtime as the objective. Leveraging the Nevergrad platform, the authors generate challenging instances for four NP‑hard problems—satisfiability, traveling salesperson, Hamiltonian cycle, and non‑permutation flow‑shop scheduling—that outperform random draws and rival curated benchmark sets. The approach requires only a solver, an instance encoder, and a compute budget, and it can uncover structural insights such as phase‑transition behavior in SAT.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv AI

Sep 30

Teaching LLMs to Generate Challenging MILP Instances via Solver Feedback

arXiv:2609.37356v1 Announce Type: new Abstract: Generating optimization instances that are both feasible and computationally challenging is crucial for benchmarking solvers and training learning-base...

By Jitin Singla, Parikshit Pareek, Pratik Jawanpuria, Parag Singla

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Sep 15

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

arXiv:2609.13443v1 Announce Type: cross Abstract: We demonstrate that training LLMs with RL does not improve performance equally across a dataset. RL shows large improvements on easy problems that an...

By Michael Noukhovitch, Hamish Ivison, Nathan Lambert, Aaron Courville

llms reinforcement-learning benchmarks

arXiv AI

5d ago

Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean

arXiv:2610.35595v1 Announce Type: new Abstract: LLMs now prove hard theorems in Lean. Can they also design algorithms and prove their correctness and efficiency? LLM-guided design of optimisation heu...

By Per Kristian Lehre

llms agents benchmarks

arXiv Computation and Language

Sep 1

AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds

arXiv:2608.29397v1 Announce Type: new Abstract: Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is...

By Zixiang Xu, Jiaan Wang, Fandong Meng

llms agents benchmarks

arXiv AI

Oct 2

OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework

The paper introduces OSCAR, an LLM‑based framework that translates business descriptions into accurate optimization models while verifying and improving them through a simulator, coder, and reviewer. OSCAR uses a cost‑ordered escalation strategy to select among LLMs of varying price and capability, achieving 95–100% accuracy on benchmark problems with local, open‑weight models. The framework also provides competitive guarantees and token‑cost advantages over existing LLMs like Codex and Claude Code.

By Jinzhi Bu, Haixin Tang, Huanan Zhang

llms benchmarks

arXiv Machine Learning

Jun 25

Learning Structural Hardness for Combinatorial Auctions: Instance-Dependent Algorithm Selection via Graph Neural Networks

arXiv:2602. 14772v2 Announce Type: replace Abstract: The Winner Determination Problem (WDP) in combinatorial auctions is NP-hard, and no existing method reliably predicts which instances will defeat fast greedy heuristics.

By Sungwoo Kang

benchmarks safety

One email a morning, machine-written

Related stories

Teaching LLMs to Generate Challenging MILP Instances via Solver Feedback

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean

AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds

OR for AI That Does OR: Routing LLMs up the Escalator inside the OSCAR Framework

Learning Structural Hardness for Combinatorial Auctions: Instance-Dependent Algorithm Selection via Graph Neural Networks