mlsanityData to 7 Oct 2026

MaestroMotif: Skill Design from Artificial Intelligence Feedback

arXiv 2412.08542 ↗First posted 11 Dec 2024cs.AI cs.CL cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabilities of Large Language Models (LLMs) to effectively create and reuse skills. It first uses an LLM's feedback to automatically design rewards corresponding to each skill, starting from their natural language description. Then, it employs an LLM's code generation abilities, together with reinforcement learning, for training the skills and combining them to implement complex behaviors specified in language. We evaluate MaestroMotif using a suite of complex tasks in the NetHack Learning Environment (NLE), demonstrating that it surpasses existing approaches in both performance and usability.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 36 of its 63 references that are in the map. First posted on arXiv 11 Dec 2024.

Builds on

36 of 63 references.

References · 36

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2017Deep reinforcement learning from human preferencescited by 3,846
  8. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  9. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  10. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  11. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  12. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
24 more
  1. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
  2. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  3. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 469
  4. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 328
  5. 2016Variational Intrinsic Controlcited by 262
  6. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 200
  7. 2020The NetHack Learning Environmentcited by 196
  8. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 145
  9. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  10. 2017A Laplacian Framework for Option Discovery in Reinforcement Learningcited by 108
  11. 2023Motif: Intrinsic Motivation from Artificial Intelligence Feedbackcited by 99
  12. 2020Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learningcited by 84
  13. 2022Does Zero-Shot Reinforcement Learning Exist?cited by 79
  14. 2024Open-Endedness is Essential for Artificial Superhuman Intelligencecited by 79
  15. 2017When Waiting is not an Option : Learning Options with a Deliberation Costcited by 57
  16. 2021Temporal Abstraction in Reinforcement Learning with the Successor Representationcited by 52
  17. 2022Exploration via Elliptical Episodic Bonusescited by 51
  18. 2020Options of Interest: Temporal Abstraction with Interest Functionscited by 30
  19. 2023Deep Laplacian-based Options for Temporally-Extended Explorationcited by 28
  20. 2024Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problemcited by 23
  21. 2024Practice Makes Perfect: Planning to Learn Skill Parameter Policiescited by 22
  22. 2022Insights From the NeurIPS 2021 NetHack Challengecited by 20
  23. 2023Embodied Lifelong Learning for Task and Motion Planningcited by 17
  24. 2022Dungeons and Data: A Large-Scale NetHack Datasetcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 12; 2026: 12.

24 papers.

Sort:

By area:

  1. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  2. 2025A Self-Improving Coding Agentcited by 58
  3. 2025LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilitiescited by 36
  4. 2025The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learningcited by 10
  5. 2025One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Explorationcited by 9
  6. 2025Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Modelscited by 5
  7. 2025Scalable Option Learning in High-Throughput Environmentscited by 5
  8. 2025ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learningcited by 5
  9. 2026SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Groundingcited by 4
  10. 2025Automated Reward Design for Gran Turismocited by 2
  11. 2025Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairscited by 2
  12. 2025Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Gamescited by 1
12 more
  1. 2026SIDiffAgent: Self-Improving Diffusion Agentcited by 1
  2. 2026Zero-Shot Instruction Following in RL via Structured LTL Representationscited by 1
  3. 2026Agentick: A Unified Benchmark for General Sequential Decision-Making Agentscited by 1
  4. 2026Multi-Agent Transactive Memorycited by 1
  5. 2025Zero-Shot Instruction Following in RL via Structured LTL Representationscited by 0
  6. 2026Hierarchical Behaviour Spacescited by 0
  7. 2026Goal-Conditioned Agents that Learn Everything All at Oncecited by 0
  8. 2026Task diversity produces systematic transfer but inhibits continual reinforcement learningcited by 0
  9. 2026SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimizationcited by 0
  10. 2026Success Leaves Detours: Learning Executable Walkthroughs for Long-Horizon Agentscited by 0
  11. 2026Up and Down the Abstraction Ladder: Code-Based Skills for Language Agentscited by 0
  12. 2026Can Jev be Your Q or Policy in Reinforcement Learning?cited by 0