# Researchers introduce MemPlan for text-based planning with PDDL

Digest AI · Research · published 2026-10-23T04:00:00Z

Canonical: https://digestai.news/story/researchers-introduce-memplan-for-text-based-planning-with-pddl

## Summary

A new framework called MemPlan bridges language models and symbolic planning for partially observable text environments. The system uses memory-conditioned PDDL planning to reconstruct problems dynamically from observations, candidate hypotheses, and interaction history. It assigns relevance-based action costs to missing objects or conditions and excludes previously refuted assumptions to improve efficiency.

MemPlan outperforms language-only and PDDL-aware baselines in task completion and step efficiency on benchmarks like TextWorld, ALFWorld, and Robotouille. It also reduces online token costs compared to LLM-planning approaches like ReAct. The same interface works across different TextWorld task types without task-specific fine-tuning. The paper and code are available on GitHub.

## Key points

- MemPlan uses PDDL planning with memory to handle partially observable text environments
- System reduces online token costs and improves task completion over LLM-planning baselines
- Interface works across TextWorld task types without additional fine-tuning

## Why it matters

MemPlan could lower costs and improve reliability for AI agents needing long-term planning in text-based tasks.

## Sources

1. [MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments](https://arxiv.org/abs/2610.30379) (arXiv cs.CL, 2026-10-23, primary source)

## Cite

Digest AI, "Researchers introduce MemPlan for text-based planning with PDDL", 23 October 2026, https://digestai.news/story/researchers-introduce-memplan-for-text-based-planning-with-pddl

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-introduce-memplan-for-text-based-planning-with-pddl.json