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

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

arXiv 25.10 2025 53.3 method

TLDR

VAGEN uses RL to train VLM agents with explicit visual state reasoning, decomposing it into state estimation and transition modeling, achieving 3x improvement.

Reasoning

The paper presents a novel RL-based approach for world model reasoning in VLM agents, with clear methodology and strong empirical results across multiple benchmarks. However, the abstract lacks details on generalization to other modalities or tasks, and the reliance on specific reasoning formats may limit applicability.

Read-first score

Read-first score 53.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 33.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%
60

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

Topical relevance 42%
47.1

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%
46

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,github

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 324.

Keyword Scores

world model
9
world dynamics prediction
7
model-based reinforcement learning world model
6
interactive world model
5
generative world model
3
world simulator
2
video world model
1

Deep Analysis

Innovations

  • Architecturally enforcing and rewarding the agent's reasoning process via reinforcement learning (RL) for VLM agents
  • Formulating the problem as a Partially Observable Markov Decision Process (POMDP)
  • Decomposing reasoning into State Estimation and Transition Modeling
  • World Modeling Reward providing dense, turn-level supervision for accurate state prediction
  • Bi-Level General Advantage Estimation (Bi-Level GAE) for turn-aware credit assignment

Methodology

The paper proposes VAGEN, a scalable framework for training multi-turn VLM agents using reinforcement learning. The agent's reasoning is decomposed into State Estimation and Transition Modeling, and a World Modeling Reward is designed to provide dense supervision. Bi-Level GAE is introduced for turn-aware credit assignment. The method is evaluated across five diverse agent benchmarks using a 3B-parameter model.

Key Results

A 3B-parameter model achieves a score of 0.82 across five benchmarks, a 3× improvement over its untrained counterpart (0.21) and outperforming proprietary models like GPT-5 (0.75), Gemini 2.5 Pro (0.67), and Claude 4.5 (0.62).

Tags