Abstract Interpretation for Generalized Heuristic Search in Model-Based Planning
On the map: World models → World models for language agents
Abstract (arXiv)
Domain-general model-based planners often derive their generality by constructing search heuristics through the relaxation or abstraction of symbolic world models. We illustrate how abstract interpretation can serve as a unifying framework for these abstraction-based heuristics, extending the reach of heuristic search to richer world models that make use of more complex datatypes and functions (e.g. sets, geometry), and even models with uncertainty and probabilistic effects. These heuristics can also be integrated with learning, allowing agents to jumpstart planning in novel world models via abstraction-derived information that is later refined by experience. This suggests that abstract interpretation can play a key role in building universal reasoning systems.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 8 of its 43 references that are in the map. First posted on arXiv 5 Aug 2022.
Builds on
8 of 43 references.
References · 8
- 2020Integrated Task and Motion Planningcited by 290
- 2019Learning Domain-Independent Planning Heuristics with Hypergraph Networkscited by 50
- 2016FFRob: Leveraging Symbolic Planning for Efficient Task and Motion Planningcited by 34
- 2019JuliaReach: a Toolbox for Set-Based Reachabilitycited by 28
- 2021Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generatorscited by 21
- 2021Generalized Planning as Heuristic Searchcited by 18
- 2017Program Synthesis using Abstraction Refinementcited by 13
- 2021Counterexample-Guided Repair for Symbolic-Geometric Action Abstractionscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
- 2025Complex LLM Planning via Automated Heuristics Discovery
- 2024Learning Abstract World Model for Value-preserving Planning with Options
- 2025General Agentic Planning Through Simulative Reasoning with World Models
- 2024Query-Efficient Planning with Language Models
- 2025Interpreting Emergent Planning in Model-Free Reinforcement Learning
- 2025Exploiting Symbolic Heuristics for the Synthesis of Domain-Specific Temporal Planning Guidance using Reinforcement Learning
- 2025Think Small, Plan Smart: Minimalist Symbolic Abstraction and Heuristic Subspace Search for LLM-Guided Task Planning