Using Large Language Models for Abstraction of Planning Domains - Extended Version

• URL: http://arxiv.org/abs/2510.20258v1
• Date: Thu, 23 Oct 2025 06:27:03 GMT
• Title: Using Large Language Models for Abstraction of Planning Domains - Extended Version
• Authors: Bita Banihashemi, Megh Patel, Yves Lespérance,
• Abstract summary: We model the agent's concrete behaviors in PDDL and investigate the use of in-context learning with large language models (LLMs)<n>We consider three categories of abstractions: abstraction of choice of alternative concrete actions, abstraction of sequences of concrete actions, and abstraction of action/predicate parameters.<n>The generated abstract PDDL domains and problem instances are then checked by symbolic validation tools as well as human experts.
• Score: 6.021787236982658
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating an abstraction of a dynamic domain that aligns with a given purpose remains a significant challenge given that the choice of such an abstraction can impact an agent's ability to plan, reason, and provide explanations effectively. We model the agent's concrete behaviors in PDDL and investigate the use of in-context learning with large language models (LLMs) for the generation of abstract PDDL domains and problem instances, given an abstraction objective specified in natural language. The benchmark examples we use are new and have not been part of the data any LLMs have been trained on. We consider three categories of abstractions: abstraction of choice of alternative concrete actions, abstraction of sequences of concrete actions, and abstraction of action/predicate parameters, as well as combinations of these. The generated abstract PDDL domains and problem instances are then checked by symbolic validation tools as well as human experts. Our experiments show that GPT-4o can generally synthesize useful planning domain abstractions in simple settings, although it is better at abstracting over actions than over the associated fluents.

Related papers

• RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems [98.98963933669751]
  We train models to be capable of proposing multiple abstractions given a problem, followed by RL that incentivizes building a solution.<n>This results in a two-player RL training paradigm, abbreviated as RLAD, that jointly trains an abstraction generator and a solution generator.<n>We show that allocating more test-time compute to generating abstractions is more beneficial for performance than generating more solutions at large test budgets.
  arXiv  Detail & Related papers  (2025-10-02T17:44:23Z)
• Causal Abstraction Inference under Lossy Representations [53.18851962820361]
  We introduce a new type of abstractions called projected abstractions that generalize existing definitions to accommodate lossy representations.<n>We show how to construct a projected abstraction from the low-level model and how it translates equivalent observational, interventional, and counterfactual causal queries from low to high-level.
  arXiv  Detail & Related papers  (2025-09-25T21:20:42Z)
• Learning Planning Abstractions from Language [28.855381137615275]
  This paper presents a framework for learning state and action abstractions in sequential decision-making domains. Our framework, planning abstraction from language (PARL), utilizes language-annotated demonstrations to automatically discover a symbolic and abstract action space.
  arXiv  Detail & Related papers  (2024-05-06T21:24:22Z)
• Learning with Language-Guided State Abstractions [58.199148890064826]
  Generalizable policy learning in high-dimensional observation spaces is facilitated by well-designed state representations. Our method, LGA, uses a combination of natural language supervision and background knowledge from language models to automatically build state representations tailored to unseen tasks. Experiments on simulated robotic tasks show that LGA yields state abstractions similar to those designed by humans, but in a fraction of the time.
  arXiv  Detail & Related papers  (2024-02-28T23:57:04Z)
• Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning [63.58935783293342]
  Causal Bisimulation Modeling (CBM) is a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. CBM's learned implicit dynamics models identify the underlying causal relationships and state abstractions more accurately than explicit ones.
  arXiv  Detail & Related papers  (2024-01-23T05:43:15Z)
• AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph [62.685920585838616]
  abstraction ability is essential in human intelligence, which remains under-explored in language models. We present AbsPyramid, a unified entailment graph of 221K textual descriptions of abstraction knowledge.
  arXiv  Detail & Related papers  (2023-11-15T18:11:23Z)
• Description Logics with Abstraction and Refinement [8.958066641323894]
  We propose an extension of description logics (DLs) in which abstraction levels are first-class citizens. We prove that reasoning in the resulting family of DLs is decidable while several seemingly harmless variations turn out to be undecidable.
  arXiv  Detail & Related papers  (2023-06-06T14:27:03Z)
• Exploiting Multiple Abstractions in Episodic RL via Reward Shaping [23.61187560936501]
  We consider a linear hierarchy of abstraction layers of the Markov Decision Process (MDP) underlying the target domain. We propose a novel form of Reward Shaping where the solution obtained at the abstract level is used to offer rewards to the more concrete MDP.
  arXiv  Detail & Related papers  (2023-02-28T13:22:29Z)
• MDP Abstraction with Successor Features [14.433551477386318]
  We study abstraction in the context of reinforcement learning, in which agents may perform state or temporal abstractions. In this work, we propose successor abstraction, a novel abstraction scheme building on successor features. Our successor abstraction allows us to learn abstract environment models with semantics that are transferable across different environments.
  arXiv  Detail & Related papers  (2021-10-18T11:35:08Z)
• Model-Invariant State Abstractions for Model-Based Reinforcement Learning [54.616645151708994]
  We introduce a new type of state abstraction called textitmodel-invariance. This allows for generalization to novel combinations of unseen values of state variables. We prove that an optimal policy can be learned over this model-invariance state abstraction.
  arXiv  Detail & Related papers  (2021-02-19T10:37:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.