Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines

arXiv 26.2 2026 47.6 method

TLDR

Proposes Contrastive World Model (CWM) using contrastive learning with hard negatives to train LLM as action feasibility scorer, outperforming SFT on ScienceWorld.

Reasoning

Strengths include a novel contrastive approach for action feasibility with hard negative mining, showing clear improvements over SFT on a benchmark. Weaknesses are limited evaluation to a single simulated benchmark (ScienceWorld) and lack of real-world robot validation, raising questions about generalizability.

Read-first score

Read-first score 47.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 24.

Recency 8%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%
70

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,evaluation,result

Topical relevance 42%
34.3

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 25%
30

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 502.

Keyword Scores

world model
9
world dynamics prediction
5
interactive world model
4
model-based reinforcement learning world model
3
world simulator
2
generative world model
1
video world model
0

Deep Analysis

Innovations

  • Contrastive World Model (CWM) for action feasibility learning in embodied agents
  • Using InfoNCE contrastive objective with hard-mined negative examples to discriminate physically correct from subtly wrong actions
  • Fine-tuning a large language model (LLM) as an action scorer with contrastive learning instead of supervised fine-tuning (SFT)

Methodology

CWM fine-tunes a large language model (LLM) as an action scorer using an InfoNCE contrastive objective with hard-mined negative examples. It is evaluated on the ScienceWorld benchmark through two studies: an intrinsic affordance evaluation on 605 hard-negative test pairs and a live filter characterisation study measuring ranking of gold-path actions against all valid environment actions during task execution.

Key Results

CWM outperforms SFT by +6.76 percentage points on Precision@1 for minimal-edit negatives and achieves a higher AUC-ROC (0.929 vs. 0.906). Under out-of-distribution stress conditions, CWM maintains a significantly better safety margin (-2.39) than SFT (-3.96).

Tags