# AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control

arXiv: https://arxiv.org/abs/2606.23079 · HTML: https://mlsanity.com/paper/2606.23079/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 20 of 20)

- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [iVideoGPT: Interactive VideoGPTs are Scalable World Models](https://mlsanity.com/paper/2405.15223/) (2024)
- [Unsupervised Learning of Object Structure and Dynamics from Videos](https://mlsanity.com/paper/1906.07889/) (2019)
- [High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks](https://mlsanity.com/paper/1911.01655/) (2019)
- [Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis](https://mlsanity.com/paper/1906.11378/) (2019)
- [VLMPC: Vision-Language Model Predictive Control for Robotic Manipulation](https://mlsanity.com/paper/2407.09829/) (2024)
- [The Power of Predictions in Online Control](https://mlsanity.com/paper/2006.07569/) (2020)
- [An Online Learning Approach to Model Predictive Control](https://mlsanity.com/paper/1902.08967/) (2019)
- [Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems](https://mlsanity.com/paper/2106.10497/) (2021)
- [A Control-Centric Benchmark for Video Prediction](https://mlsanity.com/paper/2304.13723/) (2023)
- [On the Regret Analysis of Online LQR Control with Predictions](https://mlsanity.com/paper/2102.01309/) (2021)
- [Warm Start of Mixed-Integer Programs for Model Predictive Control of Hybrid Systems](https://mlsanity.com/paper/1910.08251/) (2019)
- [Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity](https://mlsanity.com/paper/2210.12312/) (2022)
- [Multi-Object Manipulation via Object-Centric Neural Scattering Functions](https://mlsanity.com/paper/2306.08748/) (2023)
- [Online Learning for Predictive Control with Provable Regret Guarantees](https://mlsanity.com/paper/2111.15041/) (2021)

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

- [World Models for Embodied Intelligence: From Plausible to Controllable to Actionable](https://mlsanity.com/paper/2609.16697/) (2026)
- [ARC-Bench: Closed-Loop Replanning Masks Broken Action Ranking in Frozen JEPA World Models](https://mlsanity.com/paper/2609.05461/) (2026)
- [Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC](https://mlsanity.com/paper/2609.32591/) (2026)

## Abstract (arXiv)

Neural world models coupled with model predictive control (MPC) replan at every environment step to bound accumulated prediction error, but this incurs substantial computational overhead. Reusing a cached plan reduces this overhead, yet its effectiveness depends on how prediction mismatch propagates through the local dynamics. We analyze this trade-off with a perturbation-based dynamic-regret framework and show that stale-plan penalties scale with the reuse tolerance, the accumulated mismatch since the last replanning step, and the local dynamics sensitivity. Based on this structure, we propose AdaReP, a training-free wrapper that adapts the replanning tolerance online using the current deviation from the cached rollout and a local sensitivity estimate, without modifying the learned world model or planner. Across image-space planning, latent-space control, and real-world robotic manipulation, AdaReP substantially reduces planner-side computation while maintaining comparable task performance, including over 80% fewer queries on a 50-trial physical robot study.