cs.AIAug 10, 2026

verdi: retrieval is not transfer for continual world model optimization

Authors: Junyu Wu, Shiqin Nie, Youyi Kou, Baohua Yin, Guocai Yao, Qingyu Chen, Jingheng Ma, Shiji Zhou, +4 more

Organizations: * Equal contribution · ‡ Project leader, † Corresponding author · † Corresponding author

Abstract

Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence. However, optimizing a pretrained world model toward a user-specified objective remains difficult: each campaign typically rediscovers optimization strategies from scratch, and the resulting knowledge rarely transfers to the next model. Existing research agents automate the optimization loop but treat successful strategies as directly reusable recipes, without principled safeguards for when transfer is appropriate. We argue instead that retrieval is not transfer: a strategy validated on one model is at best an optimization hypothesis for another, and becomes transferable knowledge only after target-side experimental valida- tion. Guided by this principle, we propose VERDI , a continual framework for evidence-licensed world model optimization. VERDI characterizes each world model through shared inference-time probes to construct an Optimization Fin- gerprint, retrieves relevant prior experience as ranked hypotheses, and validates every candidate under a frozen target-side verifier before admitting it as reusable evidence; contradictions among nearby fingerprints further trigger probe evolution, continually refining the diagnostic representation itself. Experiments on Ctrl-World, the Cosmos family, and RoboCoin show that VERDI reduces search cost by 68%, GPU cost by 69%, and negative transfer from 0.34 to 0.06, while predicting transfer outcomes with 83% sign accuracy.

Explore similar work

CardsList
May 20, 2026cs.LG

stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation

World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols hindering reproducibility and fair comparison. Current practice is further limited by three key bottlenecks: fragile one-off codebases, slow video data loading, and the lack of standardized generalization benchmarks. We present stable-worldmodel (swm), an open-source platform for standardized and reproducible world modeling research and evaluation. It delivers (1) a high-performance Lance-based data layer with native support and conversion tools for MP4, HDF5, and LeRobot datasets, (2) clean, well-tested implementations of modern world model baselines and planning solvers, and (3) a broad suite of environments and tasks extended with controllable visual, geometric, and physical factors of variation for systematic in-silico evaluation of dynamics understanding, control performance, representation quality, and out-of-distribution generalization. By unifying the full pipeline under a single, scalable framework, \texttt{swm} dramatically reduces research overhead and accelerates trustworthy progress toward reliable world models.
Lucas Maes, Quentin Le Lidec, Luiz Facury +9
World ModelsReal-World EnvironmentsRobotic DatasetsPlatformsGeneralisation
AskPDF
Sep 11, 2026cs.LG

Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation

Continual world models must decide whether new data justify changing the model. Fixed replay schedules and prediction-error triggers specify when to update, but neither reveals the value of an individual update: one deployment run cannot show how the same model would have performed at that moment had it held its parameters. We introduce the fork ledger, which branches a deployment stream at pre-registered decision points into matched update and hold continuations under common random numbers. It evaluates both continuations on the same episodes and records ΔR=Rupdate−Rhold\Delta R = R_{\mathrm{update}} - R_{\mathrm{hold}}. Always applying one fixed update mechanism lowers return on all three simulated control tasks: CartPole (−144.0-144.0; checkpoint-bootstrap 95%95\% CI [−185.4,−116.1][-185.4,-116.1], against a converged return near 650650), Walker (−82.8-82.8; [−101.1,−61.7][-101.1,-61.7]) and Cheetah (−18.6-18.6; [−29.0,−6.6][-29.0,-6.6]). Divergence is an outcome of applying the update, so the estimand counts every attempted fork; restricted to the 693693 of 720720 that did not collapse, CartPole and Walker are unchanged in sign (−113.4-113.4 and −82.1-82.1) and Cheetah becomes unresolved (−3.9-3.9; [−17.5,+13.0][-17.5,+13.0]). The task is the unit of inference: each contributes 240240 attempted forks over five pretrained checkpoints crossed with two drift directions. The ledger makes counterfactual utility observable for a fixed mechanism, allowing triggers to be judged by the updates they select rather than by surprise detection alone.
Anqi Peter Li, Kaden Kim
Counterfactual RolloutsCounterfactual ReasoningUpdatesWorld ModelsContinuationStructured Evidence Ledger+1
AskPDF
Jun 29, 2026cs.AI

Self-Evolving World Models for LLM Agent Planning

World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unreliable foresight can be ignored, misused, or even degrade downstream decision-making. In this paper, we introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen. WorldEvolver integrates three modules: (i) Episodic Memory, which exploits real action transitions through retrieval-based simulation; (ii) Semantic Memory, which extracts persistent heuristic rules from prediction-observation mismatches; and (iii) Selective Foresight, which filters low-confidence predictions before integrating them into agent reasoning context. We evaluate WorldEvolver on ALFWorld and ScienceWorld, measuring world model prediction accuracy on Word2World and downstream agent success rate on AgentBoard. Extensive experiments show that WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate, demonstrating that test-time memory revision enhances both predictive fidelity and planning performance.
Xuan Zhang, Wenxuan Zhang, See-Kiong Ng +1
Large Language Model PlanningWorld ModelsLong-Horizon AgentsSelf-Evolving AgentsLong-Term Memory
AskPDF