# Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning

arXiv: https://arxiv.org/abs/2606.27483 · HTML: https://mlsanity.com/paper/2606.27483/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 39 of its 48 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 39)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [Android in the Wild: A Large-Scale Dataset for Android Device Control](https://mlsanity.com/paper/2307.10088/) (2023)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents](https://mlsanity.com/paper/2411.06559/) (2024)
- [OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models](https://mlsanity.com/paper/2411.04905/) (2024)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents](https://mlsanity.com/paper/2502.11357/) (2025)

## Built on by (most cited first, 3 of 3)

- [Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight](https://mlsanity.com/paper/2610.08077/) (2026)
- [Mint-Agent: Introducing Finance-Native Agentic Foundation Models](https://mlsanity.com/paper/2608.16386/) (2026)
- [Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training](https://mlsanity.com/paper/2609.33335/) (2026)

## Abstract (arXiv)

Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-horizon tasks. Unlike humans who employ "what-if" reasoning to evaluate potential plans before commitment, standard agents lack an internal world model to simulate future outcomes. Therefore, we propose to internalize future-aware planning by training a single autoregressive model to verbalize both a prospective state rollout and a plan-conditioned success estimate-a textual analogue of the Q-value. Crucially, we identify a format-capability gap: simply fine-tuning agents on look-ahead traces during post-training leads to superficial mimicry of foresight without genuine predictive grounding. To bridge this gap, we introduce a three-stage training paradigm: (i) World Model Agentic Mid-Training (WM-AMT) to inject latent predictive capabilities into the policy; (ii) Format-Eliciting SFT (FE-SFT) to structure this injected capability; and (iii) Foresight-Conditioned Reinforcement Learning (FC-RL) to refine the calibration and utility of the generated simulations. Evaluated on search and mathematical reasoning tasks, our approach consistently outperforms other training baselines. Our results demonstrate that effective internal world modeling in LLM agents requires a capability-first training pipeline to achieve grounded and calibrated foresight.