arXiv:2606. 07890v1 Announce Type: new Abstract: Performative prediction studies feedback loops that arise when predictive models are deployed in consequential domains.
arXiv:2609.14065v1 Announce Type: new Abstract: When algorithmic predictions inform people's decisions, the models we deploy are performative and actively shape the data we see. This feedback loop be...
arXiv:2602. 24207v2 Announce Type: replace Abstract: The use of algorithmic predictions in decision-making leads to a feedback loop where the models we deploy actively influence the data distributions we see, and later use to retrain on.
arXiv:2608. 02713v1 Announce Type: cross Abstract: Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize.
Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural intermediate proxy that allows agents to query lower-cost, more controllable feedback before committing to real actions.
arXiv:2602. 04402v3 Announce Type: replace-cross Abstract: Performative predictions influence the very outcomes they aim to forecast.
arXiv:2607. 15623v1 Announce Type: cross Abstract: Predictive models deployed at scale influence future data, a phenomenon called performativity.
arXiv:2606. 16933v1 Announce Type: cross Abstract: Reinforcement learning (RL) systems often degrade when operating conditions differ from those previously encountered, reflecting distributional shifts in the underlying data-generating process.
arXiv:2608. 19488v1 Announce Type: new Abstract: Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain.
arXiv:2607. 05609v1 Announce Type: cross Abstract: The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting.
arXiv:2607. 19382v1 Announce Type: cross Abstract: Deep learning models have shown strong potential for time series forecasting, yet their deployment in real-world environmental monitoring remains challenging due to non-stationary dynamics and limited explainability.
The paper introduces Retrospective World Modeling, a new paradigm for vision‑language‑model (VLM) agents that allows them to reason backward by estimating which action most likely caused a state transition. It proposes the Self‑Consistency Reward (SCR), an intrinsic signal that measures how well a policy action aligns with this retrospective explanation, providing dense transition‑level feedback. Experiments demonstrate that incorporating SCR improves policy robustness and generalization compared to purely prospective world‑modeling approaches.
arXiv:2510. 16657v3 Announce Type: replace-cross Abstract: Synthetic data has been increasingly used to train frontier generative models.