Metraipolis › archive › dc_79e103e73756
MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments — arXiv:2610.30379
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.30379
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-23T15:14:52.387Z
- SHA-256 of the archived text
b684983e3bf4aa804ce7cb633321376b8a44003910de5a3edb8fd638550cd9de- Stable URL of this page
https://metraipolis.com/documento/dc_79e103e73756
How to cite
MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments — arXiv:2610.30379 — arXiv (en), https://arxiv.org/abs/2610.30379 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_79e103e73756 (Metraipolis archive dc_79e103e73756, sha256 b684983e3bf4aa804ce7cb633321376b8a44003910de5a3edb8fd638550cd9de)
BibTeX
@misc{dc79e103e73756,
title = {MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments — arXiv:2610.30379},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.30379},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_79e103e73756; sha256 b684983e3bf4aa804ce7cb633321376b8a44003910de5a3edb8fd638550cd9de},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30379. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents are flexible in language interaction, but using them as long-horizon planners is costly and prone to hallucinated or invalid actions. This paper targets a different role for LLMs: constrained bridges between language and symbolic planning. We propose MemPlan, a memory-conditioned PDDL planning framework for partially observable interactive text environments. MemPlan keeps the PDDL domain fixed and reconstructs the PDDL problem at each step from parsed observations, candidate hypotheses, and interaction memory. Positive graph memory assigns relevance-based action costs to candidate hypotheses for missing objects, locations, or conditions, guiding the planner toward more plausible checks. Negative memory records execution-refuted assumptions and compiles them into exclusion constraints, preventing repeated attempts at candidates already contradicted by feedback. A unified schema-conditioned language--symbol interface, trained offline with supervised fine-tuning, connects text environments to the planning loop through observation-to-fact parsing and symbolic-action-to-command grounding. Experiments on TextWorld, ALFWorld, and Robotouille show that MemPlan improves task completion and step efficiency over language-only and PDDL-aware baselines, while substantially reducing online token cost compared with LLM-planning baselines such as ReAct. The same fine-tuned interface is also reused across TextWorld task types without task-specific fine-tuning. Our code and data are available at: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.30379 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-23T15:09:08.512Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).