MétaCan
Menu
Back to cohort
Record W7131998979

Enhancing the planning capabilities of large language models by building external world models

2025· article· en· W7131998979 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueNPARC · 2025
Typearticle
Languageen
FieldComputer Science
TopicAI-based Problem Solving and Planning
Canadian institutionsnot available
Fundersnot available
KeywordsBenchmark (surveying)Core (optical fiber)Baseline (sea)Plan (archaeology)Automated planning and schedulingLanguage model
DOInot available

Abstract

fetched live from OpenAlex

Large Language Models (LLMs) possess a huge amount of knowledge but struggle with multi-step planning even in toy environments due to the limitations of their static internal world model. We introduce a novel approach where an LLM serves as a “world model builder”, constructing and iteratively refining an explicit, external world model. The core of our approach is a state transition function, that is initially generated by the LLM and is refined using feedback from interactions with the environment. This refinement is made possible by accumulating test cases from past experiences allowing us to treat the construction of the world model as a program synthesis problem. We demonstrate the efficacy of our method on the Blocksworld benchmark and introduce a novel ColorMixing dataset that is designed to evaluate multi-step reasoning and planning. Our experimental results show that our method, using GPT-4 and LLaMA3- 70B, achieves perfect accuracy on Blocksworld tasks and significantly outperforms baseline methods, especially in terms of planning success and LLM queries. This paper presents a robust methodology for enhancing LLM planning via a learnable external world model and contributes a new benchmark for evaluating such capabilities.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.851
Threshold uncertainty score0.455

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.013
GPT teacher head0.265
Teacher spread0.252 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it