# Look-Ahead Reasoning on Learning Platforms

arXiv: https://arxiv.org/abs/2511.14745 · HTML: https://mlsanity.com/paper/2511.14745/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [Performative Prediction](https://mlsanity.com/paper/2002.06673/) (2020)
- [Strategic Classification](https://mlsanity.com/paper/1506.06980/) (2015)
- [Strategic Classification from Revealed Preferences](https://mlsanity.com/paper/1710.07887/) (2017)
- [The Mechanics of n-Player Differentiable Games](https://mlsanity.com/paper/1802.05642/) (2018)
- [Stochastic Optimization for Performative Prediction](https://mlsanity.com/paper/2006.06887/) (2020)
- [Performative Prediction in a Stateful World](https://mlsanity.com/paper/2011.03885/) (2020)
- [Strategic Classification in the Dark](https://mlsanity.com/paper/2102.11592/) (2021)
- [Stochastic optimization with decision-dependent distributions](https://mlsanity.com/paper/2011.11173/) (2020)
- [Who Leads and Who Follows in Strategic Classification?](https://mlsanity.com/paper/2106.12529/) (2021)
- [Performative Prediction: Past and Future](https://mlsanity.com/paper/2310.16608/) (2023)
- [Information Discrepancy in Strategic Learning](https://mlsanity.com/paper/2103.01028/) (2021)
- [Alternative Microfoundations for Strategic Classification](https://mlsanity.com/paper/2106.12705/) (2021)
- [Multiplayer Performative Prediction: Learning in Decision-Dependent Games](https://mlsanity.com/paper/2201.03398/) (2022)
- [Performative Power](https://mlsanity.com/paper/2203.17232/) (2022)
- [Adversarial Search Engine Optimization for Large Language Models](https://mlsanity.com/paper/2406.18382/) (2024)
- [Generalized Strategic Classification and the Case of Aligned Incentives](https://mlsanity.com/paper/2202.04357/) (2022)
- [Algorithmic Collective Action in Machine Learning](https://mlsanity.com/paper/2302.04262/) (2023)
- [POTs: Protective Optimization Technologies](https://mlsanity.com/paper/1806.02711/) (2018)
- [Data Leverage: A Framework for Empowering the Public in its Relationship with Technology Companies](https://mlsanity.com/paper/2012.09995/) (2020)
- [The Role of Learning Algorithms in Collective Action](https://mlsanity.com/paper/2405.06582/) (2024)
- [Decline Now: A Combinatorial Model for Algorithmic Collective Action](https://mlsanity.com/paper/2410.12633/) (2024)
- [Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists](https://mlsanity.com/paper/2404.04269/) (2024)
- [Statistical Collusion by Collectives on Learning Platforms](https://mlsanity.com/paper/2502.04879/) (2025)
- [Incentive-Aware Machine Learning; Robustness, Fairness, Improvement & Causality](https://mlsanity.com/paper/2505.05211/) (2025)

## Built on by (most cited first, 2 of 2)

- [Partially Performative Prediction](https://mlsanity.com/paper/2606.07890/) (2026)
- [Performative Privacy: When Differential Privacy Maximizes Utility](https://mlsanity.com/paper/2608.28198/) (2026)

## Abstract (arXiv)

On many learning platforms, the optimization criteria guiding model training reflect the priorities of the designer rather than those of the individuals they affect. Consequently, users may act strategically to obtain more favorable outcomes. While past work has studied strategic user behavior on learning platforms, the focus has largely been on strategic responses to a deployed model, without considering the behavior of other users. In contrast, look-ahead reasoning takes into account that user actions are coupled, and -- at scale -- impact future predictions. Within this framework, we first formalize level-k thinking, a concept from behavioral economics, where users aim to outsmart their peers by looking one step ahead. We show that, while convergence to an equilibrium is accelerated, the equilibrium remains the same, providing no benefit of higher-level reasoning for individuals in the long run. Then, we focus on collective reasoning, where users take coordinated actions by optimizing through their joint impact on the model. By contrasting collective with selfish behavior, we characterize the benefits and limits of coordination; a new notion of alignment between the learner's and the users' utilities emerges as a key concept. Look-ahead reasoning can be seen as a generalization of algorithmic collective action; we thus offer the first results characterizing the utility trade-offs of coordination when contesting algorithmic systems.