Imagen de Portada

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Carta, Thomas, Romac, Clément, Gaven, Loris, Oudeyer, Pierre-Yves, Sigaud, Olivier, Lamprier, Sylvain
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
por: Gaven, Loris, et al.
Publicado: (2024)

Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
por: Carta, Thomas, et al.
Publicado: (2023)

MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
por: Gaven, Loris, et al.
Publicado: (2025)

Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
por: Aissi, Mohamed Salim, et al.
Publicado: (2024)

WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making
por: Levy, Guillaume, et al.
Publicado: (2025)

Imagine Beyond! Distributionally Robust Auto-Encoding for State Space Coverage in Online Reinforcement Learning
por: Castanet, Nicolas, et al.
Publicado: (2025)

Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey
por: Colas, Cédric, et al.
Publicado: (2020)

LogProber: Disentangling confidence from contamination in LLM responses
por: Yax, Nicolas, et al.
Publicado: (2024)

Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning
por: Goudet, Olivier, et al.
Publicado: (2025)

Improved Performances and Motivation in Intelligent Tutoring Systems: Combining Machine Learning and Learner Choice
por: Clément, Benjamin, et al.
Publicado: (2024)

Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning
por: Canesse, Alexi, et al.
Publicado: (2024)

Deinterleaving of Discrete Renewal Process Mixtures with Application to Electronic Support Measures
por: Pinsolle, Jean, et al.
Publicado: (2024)

PhyloLM : Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks
por: Yax, Nicolas, et al.
Publicado: (2024)

Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment
por: Petitbois, Mathieu, et al.
Publicado: (2026)

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
por: Pourcel, Julien, et al.
Publicado: (2025)

Reward-Preserving Attacks For Robust Reinforcement Learning
por: Schott, Lucas, et al.
Publicado: (2026)

RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms
por: Asri, Zakariae El, et al.
Publicado: (2025)

CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
por: Colas, Cédric, et al.
Publicado: (2018)

A tale of two goals: leveraging sequentiality in multi-goal scenarios
por: Serris, Olivier, et al.
Publicado: (2025)

Discovering Sensorimotor Agency in Cellular Automata using Diversity Search
por: Hamon, Gautier, et al.
Publicado: (2024)

Offline Learning of Controllable Diverse Behaviors
por: Petitbois, Mathieu, et al.
Publicado: (2025)

ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models
por: Pourcel, Julien, et al.
Publicado: (2023)

Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
por: Asri, Zakariae El, et al.
Publicado: (2024)

A Transformer Model for Predicting Chemical Products from Generic SMARTS Templates with Data Augmentation
por: Ozer, Derin, et al.
Publicado: (2025)

A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
por: Sigaud, Olivier, et al.
Publicado: (2023)

Agentic Adversarial QA for Improving Domain-Specific LLMs
por: Grari, Vincent, et al.
Publicado: (2026)

SkillRouter: Skill Routing for LLM Agents at Scale
por: Zheng, YanZhao, et al.
Publicado: (2026)

ACT: Agentic Classification Tree
por: Grari, Vincent, et al.
Publicado: (2025)

Harnessing Superclasses for Learning from Hierarchical Databases
por: Urbani, Nicolas, et al.
Publicado: (2024)

Bootstrapping Fuzzers for Compilers of Low-Resource Language Dialects Using Language Models
por: Vaidya, Sairam, et al.
Publicado: (2025)

LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval
por: Gupta, Nilesh, et al.
Publicado: (2025)

Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?
por: Kovač, Grgur, et al.
Publicado: (2025)

Stick to your Role! Stability of Personal Values Expressed in Large Language Models
por: Kovač, Grgur, et al.
Publicado: (2024)

EPO: Hierarchical LLM Agents with Environment Preference Optimization
por: Zhao, Qi, et al.
Publicado: (2024)

Robotic Skill Diversification via Active Mutation of Reward Functions in Reinforcement Learning During a Liquid Pouring Task
por: van Buuren, Jannick, et al.
Publicado: (2025)

Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
por: Schott, Lucas, et al.
Publicado: (2024)

Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks
por: Shen, William F., et al.
Publicado: (2026)

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
por: Wang, Hao, et al.
Publicado: (2026)

PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
por: Kirscher, Tristan, et al.
Publicado: (2025)

TWISTED-RL: Hierarchical Skilled Agents for Knot-Tying without Human Demonstrations
por: Freund, Guy, et al.
Publicado: (2026)