Hugging Face Trending Papers July 13, 2026

RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience

Read the original on Hugging Face Trending Papers →

Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods have shown promise, they predominantly rely on fixed evolutionary operators and struggle to effectively accumulate and reuse historical search experience.

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 Hugging Face Trending Papers.

arXiv AI

Sep 1

ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback

arXiv:2604.04940v3 Announce Type: replace Abstract: Designing effective heuristics for NP-hard combinatorial optimization problems remains challenging and often requires substantial domain expertise....

By Cuong Van Duc, Minh Nguyen Dinh Tuan, Tam Vu Duc, Tung Vu Duy, Son Nguyen Van, Hanh Nguyen Thi, Binh Huynh Thi Thanh

llms benchmarks

arXiv AI

Sep 12

MAPLE: Memory-Augmented Planning with Language and Evolution

MAPLE is a new agent that maintains and updates optimization problems through successive natural‑language requests, combining language‑based problem construction with mathematical programming and evolutionary search. It preserves the optimization program, accepted plans, earlier updates, and candidate solutions for future requests, enabling rapid adaptation to changing business constraints. In a benchmark of 15 trajectories and 180 updates across various operational domains, MAPLE completed all trajectories with high online scalar quality and Pareto hypervolume ratio, and maintained update validity and useful search information across substantial revisions.

By Kesheng Chen, Yamin Hu, Wenjian Luo

llms agents benchmarks

arXiv AI

Jun 2

LLM-Evolved Pattern Generators for Optimal Classical Planning

arXiv:2606. 02438v1 Announce Type: new Abstract: Learned heuristics have recently become a competitive alternative to traditional domain-independent heuristics for satisficing planning.

By Windy Phung, Dominik Drexler, Arnaud Lequen, Jendrik Seipp

llms benchmarks

arXiv AI

Jul 9

Successor-Generator Planning with LLM-generated Heuristics

arXiv:2501. 18784v5 Announce Type: replace Abstract: Heuristics are a central component of deterministic planning, particularly in domain-independent settings where general applicability is prioritized over task-specific tuning.

By Alexander Tuisov, Yonatan Vernik, Alexander Shleyfman

llms benchmarks

arXiv AI

Aug 14

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design

arXiv:2605. 08756v2 Announce Type: replace Abstract: Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs).

By Haoze Lv, Ning Lu, Ziang Zhou, Yew-Soon Ong, Shengcai Liu

llms agents reinforcement-learning benchmarks

arXiv Machine Learning

Sep 2

ES-AHD: An Evolution Strategy Framework for Automatic Heuristic Design

arXiv:2609.00023v1 Announce Type: cross Abstract: In this paper, we introduce ES-AHD, a novel framework that fundamentally integrates Evolution Strategy (ES) into Large Language Model (LLM)-driven Au...

By Yutao Lai, Kezhao Lai, Hai-Lin Liu, Yuping Wang, Ping Guo

llms rag

One email a morning, machine-written

Related stories

ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback

MAPLE: Memory-Augmented Planning with Language and Evolution

LLM-Evolved Pattern Generators for Optimal Classical Planning

Successor-Generator Planning with LLM-generated Heuristics

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design

ES-AHD: An Evolution Strategy Framework for Automatic Heuristic Design