Research map / Multi-agent systems and games / Games and equilibria
Strategic classification
Models classifiers facing agents who adapt features, with incentives and causal analysis.
51 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Games and equilibria, keyword cluster “principal · strategic · welfare”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
12 papers in 2023–24 and 17 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 9.4% to 11.9%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Strategyproof Peer Selection: Mechanisms, Analyses, and Experiments (AAAI 2016 · 37 citations)
- 2018 · Reinforcement Mechanism Design for Fraudulent Behaviour in e-Commerce (AAAI 2018 · 38 citations)
- 2019 · Distinguishing Distributions When Samples Are Strategically Transformed (NeurIPS 2019 · 7 citations)
- 2020 · Information Elicitation Mechanisms for Statistical Estimation (AAAI 2020 · 11 citations)
- 2021 · Catch Me if I Can: Detecting Strategic Behaviour in Peer Assessment (AAAI 2021 · 16 citations)
- 2022 · Bayesian Persuasion in Sequential Decision-Making (AAAI 2022 · 10 citations)
- 2023 · OPRADI: Applying Security Game to Fight Drive under the Influence in Real-World (AAAI 2023 · 0 citations)
- 2024 · Bayesian Strategic Classification (NeurIPS 2024 · 3 citations)
- 2025 · Bayesian Persuasion with Externalities: Exploiting Agent Types (AAAI 2025 · 0 citations)
- 2026 · Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics (ICML 2026 · 0 citations)
Earliest papers here
- Strategyproof Peer Selection: Mechanisms, Analyses, and Experiments (AAAI 2016 · 37 citations)
- Eliciting Categorical Data for Optimal Aggregation (NeurIPS 2016 · 10 citations)
- Personalized Alert Agent for Optimal User Performance (AAAI 2016 · 7 citations)
What has been tried
37 papers here report 268 measured changes (a component added, removed or swapped, compared with a baseline): helped 57%, no clear effect 13%, hurt 22%, mixed 7%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Use a probabilistic sampler instead of hard model labels for model-annotated samples | Strategic-agent population · acceptance rate | No clear effect | Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions (NeurIPS 2024 · 1 citation) | |
| Remove the gradient through the principal's action choice | Toy environment, previously performative model · performativity | Hurt | Joint Scoring Rules: Competition Between Agents Avoids Performative Prediction (AAAI 2025 · 0 citations) | |
| Use the ρ-partition mechanism with ρ=1 instead of ρ=\frac{1}{2} | General approval voting, k-selection · consistency | 1-\frac{1}{2k} -> 1 | Helped | Impartial Selection with Predictions (NeurIPS 2025 · 0 citations) |
| reduce the number of judgments by subsampling at rate α ≥ 0.4 | Chess · ordinal accuracy | No clear effect | Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction (NeurIPS 2024 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 29 papers; from OpenAlex and the papers' affiliations).
- Harvard University · 3 papers
- University of Oxford · 2 papers
- Cornell University · 2 papers
- University of Michigan - Ann Arbor · 2 papers
- Carnegie Mellon University · 2 papers
- Toyota Technological Institute at Chicago · 2 papers
- Massachusetts Institute of Technology · 2 papers
- Georgia Institute of Technology · 2 papers
Use it
Download BibTeX of 38 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Fair division and coalition formation (99 papers)
- Learning with strategic agents (74 papers)
Elsewhere in the topic
- Learning in Markov games (111 papers)
- Cooperation and social dilemmas (95 papers)
- Opponent modeling in competitive games (75 papers)
- Mean-field game learning (21 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).