Cover Image

Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Haoyu, Song, Yuliang, Li, Tao, Deng, Zhiwei, Wang, Yaqing, Ramachandran, Deepak, Cohen, Eldan, Roth, Dan
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CP-SynC: Multi-Agent Zero-Shot Constraint Modeling in MiniZinc with Synthesized Checkers
by: Song, Yuliang, et al.
Published: (2026)

Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models
by: Zhao, Junda, et al.
Published: (2025)

Devil's Advocate: Anticipatory Reflection for LLM Agents
by: Wang, Haoyu, et al.
Published: (2024)

Transport, Don't Generate: Deterministic Geometric Flows for Combinatorial Optimization
by: Friedmann, Benjy, et al.
Published: (2026)

An Amortized Efficiency Threshold for Comparing Neural and Heuristic Solvers in Combinatorial Optimization
by: Afifi, Sohaib
Published: (2026)

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

Enhancing CVRP Solver through LLM-driven Automatic Heuristic Design
by: Xie, Zhuoliang, et al.
Published: (2026)

Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization
by: Wang, Rongzheng, et al.
Published: (2026)

Neural Solver Selection for Combinatorial Optimization
by: Gao, Chengrui, et al.
Published: (2024)

Don't Just Fine-tune the Agent, Tune the Environment
by: Lu, Siyuan, et al.
Published: (2025)

Aligning LLMs with Graph Neural Solvers for Combinatorial Optimization
by: Feng, Shaodi, et al.
Published: (2026)

Don't Make the LLM Read the Graph: Make the Graph Think
by: Sun, Yuqi, et al.
Published: (2026)

Boosting Cross-problem Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time Adaptation
by: Lei, Haoyu, et al.
Published: (2025)

Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
by: An, Sohyun, et al.
Published: (2025)

Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristic
by: Li, Haoming, et al.
Published: (2024)

Don't Pay Attention
by: Hammoud, Mohammad, et al.
Published: (2025)

Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
by: Russinovich, Mark, et al.
Published: (2024)

Don't be Tricked by Iterative Masking
by: Evan Crothers, et al.
Published: (2026)

Large Language Models as End-to-end Combinatorial Optimization Solvers
by: Jiang, Xia, et al.
Published: (2025)

AUTOCT: Automating Interpretable Clinical Trial Prediction with LLM Agents
by: Liu, Fengze, et al.
Published: (2025)

Do Retrieval Augmented Language Models Know When They Don't Know?
by: Zhou, Youchao, et al.
Published: (2025)

Don't Look Away
by: Cohen, Brianne
Published: (2023)

Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
by: Zhou, Jin Peng, et al.
Published: (2024)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
by: Hassid, Michael, et al.
Published: (2025)

DISCO: Efficient Diffusion Solver for Large-Scale Combinatorial Optimization Problems
by: Zhao, Hang, et al.
Published: (2024)

Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation
by: Verdù, Federico Julian Camerota, et al.
Published: (2024)

LLM Cyber Evaluations Don't Capture Real-World Risk
by: Lukošiūtė, Kamilė, et al.
Published: (2025)

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
by: Zhang, Jiefu, et al.
Published: (2026)

What Papers Don't Tell You: Recovering Tacit Knowledge for Automated Paper Reproduction
by: Li, Lehui, et al.
Published: (2026)

Don't Forget Imagination!
by: Vityaev, Evgenii E., et al.
Published: (2025)

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
by: Xu, Zaiyan, et al.
Published: (2025)

Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces
by: Zhang, Yilin, et al.
Published: (2026)

Hard Constraints Meet Soft Generation: Guaranteed Feasibility for LLM-based Combinatorial Optimization
by: Liu, Yang, et al.
Published: (2026)

Efficient Neural Combinatorial Optimization Solver for the Min-max Heterogeneous Capacitated Vehicle Routing Problem
by: Wu, Xuan, et al.
Published: (2025)

sDPO: Don't Use Your Data All at Once
by: Kim, Dahyun, et al.
Published: (2024)

Don't Judge by the Look: Towards Motion Coherent Video Representation
by: Zhang, Yitian, et al.
Published: (2024)

Don’t Give It Away: The Hidden Risks of Generative AI for Scientists
by: Brandão, Anarosa
Published: (2026)

Don't Fear Peculiar Activation Functions: EUAF and Beyond
by: Wang, Qianchao, et al.
Published: (2024)

Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target
by: Kim, Taesan, et al.
Published: (2026)

Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
by: Sun, Zhensu, et al.
Published: (2022)