mlsanityData to 7 Oct 2026

Model Space Reasoning as Search in Feedback Space for Planning Domain Generation

arXiv 2604.08712 ↗First posted 9 Apr 2026cs.AIcited by 1

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

The generation of planning domains from natural language descriptions remains an open problem even with the advent of large language models and reasoning models. Recent work suggests that while LLMs have the ability to assist with domain generation, they are still far from producing high quality domains that can be deployed in practice. To this end, we investigate the ability of an agentic language model feedback framework to generate planning domains from natural language descriptions that have been augmented with a minimal amount of symbolic information. In particular, we evaluate the quality of the generated domains under various forms of symbolic feedback, including landmarks, and output from the VAL plan validator. Using these feedback mechanisms, we experiment using heuristic search over model space to optimize domain quality.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 9 of its 21 references that are in the map. First posted on arXiv 9 Apr 2026.

Builds on

9 of 21 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Generating Symbolic World Models via Test-time Scaling of Large Language Models7 Feb
  2. 2023Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning22 Nov

Other references · 7

  1. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 204
  2. 2023ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planningcited by 77
  3. 2024Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languagescited by 32
  4. 2025Text2World: Benchmarking Large Language Models for Symbolic World Model Generationcited by 25
  5. 2024NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptionscited by 22
  6. 2024Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Modelscited by 17
  7. 2024Planning in the Dark: LLM-Symbolic Planning Pipeline without Expertscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Grounded Evaluation and Repair for NL-to-PDDL Problem Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning
  2. 2023On the Planning Abilities of Large Language Models : A Critical Investigation
  3. 2023On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)
  4. 2025Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
  5. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change
  6. 2025Deliberate Planning in Language Models with Symbolic Representation
  7. 2024Query-Efficient Planning with Language Models
  8. 2022Plansformer: Generating Symbolic Plans using Transformers