mlsanityData to 14 Oct 2026

Empowering LLMs with Parameterized Skills for Adversarial Long-Horizon Planning

arXiv 2509.13127 ↗First posted 16 Sep 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advancements in Large Language Models(LLMs) have led to the development of LLM-based AI agents. A key challenge is the creation of agents that can effectively ground themselves in complex, adversarial long-horizon environments. Existing methods mainly focus on (1) using LLMs as policies to interact with the environment through generating low-level feasible actions, and (2) utilizing LLMs to generate high-level tasks or language guides to stimulate action generation. However, the former struggles to generate reliable actions, while the latter relies heavily on expert experience to translate high-level tasks into specific action sequences. To address these challenges, we introduce the Plan with Language, Act with Parameter (PLAP) planning framework that facilitates the grounding of LLM-based agents in long-horizon environments. The PLAP method comprises three key components: (1) a skill library containing environment-specific parameterized skills, (2) a skill planner powered by LLMs, and (3) a skill executor converting the parameterized skills into executable action sequences. We implement PLAP in MicroRTS, a long-horizon real-time strategy game that provides an unfamiliar and challenging environment for LLMs. The experimental results demonstrate the effectiveness of PLAP. In particular, GPT-4o-driven PLAP in a zero-shot setting outperforms 80% of baseline agents, and Qwen2-72B-driven PLAP, with carefully crafted few-shot examples, surpasses the top-tier scripted agent, CoacAI. Additionally, we design comprehensive evaluation metrics and test 6 closed-source and 2 open-source LLMs within the PLAP framework, ultimately releasing an LLM leaderboard ranking long-horizon skill planning ability. Our code is available at https://github.com/AI-Research-TeamX/PLAP.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 54 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

39 of 54 references.

References · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  8. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  10. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  11. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  12. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
27 more
  1. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  2. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  3. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  4. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 529
  5. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
  6. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 274
  7. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  8. 2024Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Modelscited by 178
  9. 2023Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approachcited by 79
  10. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 67
  11. 2015Reinforcement Learning with Parameterized Actionscited by 63
  12. 2024Large Language Model Agent in Financial Trading: A Surveycited by 60
  13. 2024Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Taskscited by 52
  14. 2017Multi-Level Discovery of Deep Optionscited by 51
  15. 2023SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledgecited by 49
  16. 2017DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrationscited by 43
  17. 2024LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environmentscited by 32
  18. 2022Large Language Models can Implement Policy Iterationcited by 31
  19. 2023Large Language Model as a Policy Teacher for Training Reinforcement Learning Agentscited by 30
  20. 2023Introspective Tips: Large Language Model for In-Context Decision Makingcited by 28
  21. 2024Grounding LLMs For Robot Task Planning Using Closed-loop State Feedbackcited by 25
  22. 2024Practice Makes Perfect: Planning to Learn Skill Parameter Policiescited by 23
  23. 2022Generating Executable Action Plans with Environmentally-Aware Language Modelscited by 21
  24. 2021Gym-μRTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learningcited by 19
  25. 2020Modeling Long-horizon Tasks as Sequential Interaction Landscapescited by 14
  26. 2019Motion Perception in Reinforcement Learning with Dynamic Objectscited by 13
  27. 2024Multi-granularity Knowledge Transfer for Continual Reinforcement Learningcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
  2. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
  3. 2026A Subgoal-driven Framework for Improving Long-Horizon LLM Agents
  4. 2024Understanding the planning of LLM agents: A survey
  5. 2024Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example
  6. 2026Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
  7. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
  8. 2026Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks