Imagen de Portada

MeLA: A Metacognitive LLM-Driven Architecture for Automatic Heuristic Design

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qiu, Zishang, Chen, Xinan, Chen, Long, Bai, Ruibin
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Genetic Programming with Reinforcement Learning Trained Transformer for Real-World Dynamic Scheduling Problems
por: Chen, Xinan, et al.
Publicado: (2025)

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

Preference-Agile Multi-Objective Optimization for Real-time Vehicle Dispatching
por: Jin, Jiahuan, et al.
Publicado: (2026)

PyVRP$^+$: LLM-Driven Metacognitive Heuristic Evolution for Hybrid Genetic Search in Vehicle Routing Problems
por: Malik, Manuj, et al.
Publicado: (2026)

RoCo: Role-Based LLMs Collaboration for Automatic Heuristic Design
por: Xu, Jiawei, et al.
Publicado: (2025)

HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs
por: Dat, Pham Vu Tuan, et al.
Publicado: (2024)

Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design
por: Zheng, Zhi, et al.
Publicado: (2025)

G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design
por: Zhao, Baoyun, et al.
Publicado: (2026)

HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design
por: Chen, Chentong, et al.
Publicado: (2025)

TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Design
por: Chen, Chentong, et al.
Publicado: (2026)

Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach
por: Tan, Zhen, et al.
Publicado: (2024)

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
por: Lv, Haoze, et al.
Publicado: (2026)

QUBE: Enhancing Automatic Heuristic Design via Quality-Uncertainty Balanced Evolution
por: Chen, Zijie, et al.
Publicado: (2024)

VRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problems
por: Hottung, André, et al.
Publicado: (2025)

ReMe: Scaffolding Personalized Cognitive Training via Controllable LLM-Mediated Conversations
por: Wang, Zilong, et al.
Publicado: (2024)

Automatic Reward Shaping from Multi-Objective Human Heuristics
por: Xie, Yuqing, et al.
Publicado: (2025)

Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning
por: Sun, Zexu, et al.
Publicado: (2025)

Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
por: Chen, Sirui, et al.
Publicado: (2026)

AutoRNet: Automatically Optimizing Heuristics for Robust Network Design via Large Language Models
por: Yu, He, et al.
Publicado: (2024)

Rescaling Confidence: What Scale Design Reveals About LLM Metacognition
por: Dai, Yuyang
Publicado: (2026)

Experience-Guided Reflective Co-Evolution of Prompts and Heuristics for Automatic Algorithm Design
por: Liu, Yihong, et al.
Publicado: (2025)

LLM-Driven Heuristic Synthesis for Industrial Process Control: Lessons from Hot Steel Rolling
por: Siboni, Nima H., et al.
Publicado: (2026)

Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
por: Liu, Fei, et al.
Publicado: (2024)

Boosting Universal LLM Reward Design through Heuristic Reward Observation Space Evolution
por: Heng, Zen Kit, et al.
Publicado: (2025)

Algorithmic Prompt-Augmentation for Efficient LLM-Based Heuristic Design for A* Search
por: Bömer, Thomas, et al.
Publicado: (2026)

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
por: Zhuang, Ziqing, et al.
Publicado: (2026)

Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis
por: Fan, Zhilin, et al.
Publicado: (2026)

EoH-S: Evolution of Heuristic Set using LLMs for Automated Heuristic Design
por: Liu, Fei, et al.
Publicado: (2025)

When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems
por: Cheng, Z., et al.
Publicado: (2026)

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

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

Know the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System Design
por: Li, Zhenkun, et al.
Publicado: (2025)

SiamNAS: Siamese Surrogate Model for Dominance Relation Prediction in Multi-objective Neural Architecture Search
por: Zhou, Yuyang, et al.
Publicado: (2025)

Successor-Generator Planning with LLM-generated Heuristics
por: Tuisov, Alexander, et al.
Publicado: (2025)

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

Enhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment
por: Askin, Deniz, et al.
Publicado: (2026)

In-the-loop Hyper-Parameter Optimization for LLM-Based Automated Design of Heuristics
por: van Stein, Niki, et al.
Publicado: (2024)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
por: Didolkar, Aniket, et al.
Publicado: (2025)

Scaffolding Metacognition in Programming Education: Understanding Student-AI Interactions and Design Implications
por: Ma, Boxuan, et al.
Publicado: (2025)

Complex LLM Planning via Automated Heuristics Discovery
por: Ling, Hongyi, et al.
Publicado: (2025)