Using Reasoning Models to Generate Search Heuristics that Solve Open Instances of Combinatorial Design Problems

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
1. Verfasser:	Rosin, Christopher D.
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Artificial Intelligence Computation and Language Combinatorics
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Using Code Generation to Solve Open Instances of Combinatorial Design Problems
von: Rosin, Christopher D.
Veröffentlicht: (2025)

Automated Discovery of Improved Constant Weight Binary Codes
von: Rosin, Christopher D.
Veröffentlicht: (2026)

BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
von: Wang, Teng, et al.
Veröffentlicht: (2024)

Exploring Combinatorial Problem Solving with Large Language Models: A Case Study on the Travelling Salesman Problem Using GPT-3.5 Turbo
von: Masoud, Mahmoud, et al.
Veröffentlicht: (2024)

FCoReBench: Can Large Language Models Solve Challenging First-Order Combinatorial Reasoning Problems?
von: Mittal, Chinmay, et al.
Veröffentlicht: (2024)

Empirical Analysis Of Heuristic and Approximation Algorithms for the The Mutual-Visibility Problem
von: Stojanović, Vanja, et al.
Veröffentlicht: (2025)

Polymorphic Combinatorial Frameworks (PCF): Guiding the Design of Mathematically-Grounded, Adaptive AI Agents
von: Pearl, David, et al.
Veröffentlicht: (2025)

Reinforced Generation of Combinatorial Structures: Ramsey Numbers
von: Nagda, Ansh, et al.
Veröffentlicht: (2026)

CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMs
von: Wang, Kangsheng, et al.
Veröffentlicht: (2024)

Multi-LLM Collaborative Search for Complex Problem Solving
von: Yang, Sen, et al.
Veröffentlicht: (2025)

Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design
von: Xia, Hai, et al.
Veröffentlicht: (2026)

Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning
von: Kim, Jonathan, et al.
Veröffentlicht: (2025)

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning
von: Singhi, Nishad, et al.
Veröffentlicht: (2025)

Solving an Open Problem in Theoretical Physics using AI-Assisted Discovery
von: Brenner, Michael P., et al.
Veröffentlicht: (2026)

Reinforced Generation of Combinatorial Structures: Hardness of Approximation
von: Nagda, Ansh, et al.
Veröffentlicht: (2025)

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
von: Parmar, Mihir, et al.
Veröffentlicht: (2025)

Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving
von: Gao, Songyang, et al.
Veröffentlicht: (2025)

Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving
von: Xu, Xin, et al.
Veröffentlicht: (2025)

An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems
von: Shaik, Hashmath, et al.
Veröffentlicht: (2024)

Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model
von: Qian, Cheng, et al.
Veröffentlicht: (2023)

Using Combinatorial Optimization to Design a High quality LLM Solution
von: Ackerman, Samuel, et al.
Veröffentlicht: (2024)

CT Open: An Open-Access, Uncontaminated, Live Platform for the Open Challenge of Clinical Trial Outcome Prediction
von: Wang, Jianyou, et al.
Veröffentlicht: (2026)

Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning
von: Ma, Xuetao, et al.
Veröffentlicht: (2025)

ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
von: Gou, Zhibin, et al.
Veröffentlicht: (2023)

HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization
von: Chen, Hongzheng, et al.
Veröffentlicht: (2025)

CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization
von: Sun, Weiwei, et al.
Veröffentlicht: (2025)

Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages
von: Chen, Zui, et al.
Veröffentlicht: (2025)

Large Language Models Are Self-Taught Reasoners: Enhancing LLM Applications via Tailored Problem-Solving Demonstrations
von: Ong, Kai Tzu-iunn, et al.
Veröffentlicht: (2024)

Solving Combinatorial Counting Problems with Weighted First-Order Model Counting
von: Wang, Yuanhong, et al.
Veröffentlicht: (2026)

Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving
von: Zheng, Shunfeng, et al.
Veröffentlicht: (2025)

BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design
von: Xiang, Chuyang, et al.
Veröffentlicht: (2026)

Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization
von: Esencan, Mert, et al.
Veröffentlicht: (2024)

AlphaMapleSAT: An MCTS-based Cube-and-Conquer SAT Solver for Hard Combinatorial Problems
von: Jha, Piyush, et al.
Veröffentlicht: (2024)

Reinforcement Learning Problem Solving with Large Language Models
von: Gholamian, Sina, et al.
Veröffentlicht: (2024)

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
von: Li, Yubo, et al.
Veröffentlicht: (2026)

Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models
von: Ignat, Oana, et al.
Veröffentlicht: (2023)

Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models
von: Han, Simeng, et al.
Veröffentlicht: (2025)

Conceptual In-Context Learning and Chain of Concepts: Solving Complex Conceptual Problems Using Large Language Models
von: Vaidya, Nishtha N., et al.
Veröffentlicht: (2024)

From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning
von: Dinucu-Jianu, David, et al.
Veröffentlicht: (2025)

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
von: Qu, Yuxiao, et al.
Veröffentlicht: (2025)