Research map / Learning theory and algorithms / Submodular and game algorithms
Opponent modeling and subgame solving
Use search, subgame refinement and meta-learning to play against opponents in imperfect-information games.
116 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Submodular and game algorithms, keyword cluster “game · equilibrium · equilibria”
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.
20 papers in 2023–24 and 31 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 9.9% to 12.8%.
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 · One Size Does Not Fit All: A Game-Theoretic Approach for Dynamically and Effectively Screening for Threats (AAAI 2016 · 43 citations)
- 2017 · Safe and Nested Subgame Solving for Imperfect-Information Games (NeurIPS 2017 · 98 citations)
- 2018 · Computational Results for Extensive-Form Adversarial Team Games (AAAI 2018 · 32 citations)
- 2019 · Multiagent Evaluation under Incomplete Information (NeurIPS 2019 · 21 citations)
- 2020 · To Signal or Not To Signal: Exploiting Uncertain Real-Time Information in Signaling Games for Security and Sustainability (AAAI 2020 · 16 citations)
- 2021 · Modelling Behavioural Diversity for Learning in Open-Ended Games (ICML 2021 · 13 citations)
- 2022 · When Can the Defender Effectively Deceive Attackers in Security Games? (AAAI 2022 · 7 citations)
- 2023 · Modeling content creator incentives on algorithm-curated platforms (ICLR 2023 · 7 citations)
- 2024 · Pay to (Not) Play: Monetizing Impatience in Mobile Games (AAAI 2024 · 6 citations)
- 2025 · On the Power of Strategic Corpus Enrichment in Content Creation Games (AAAI 2025 · 3 citations)
- 2026 · Leaderboard Incentives: Model Rankings under Strategic Post-Training (ICML 2026 · 0 citations)
Earliest papers here
- One Size Does Not Fit All: A Game-Theoretic Approach for Dynamically and Effectively Screening for Threats (AAAI 2016 · 43 citations)
- Computing Optimal Monitoring Strategy for Detecting Terrorist Plots (AAAI 2016 · 36 citations)
- Complexity of Hedonic Games with Dichotomous Preferences (AAAI 2016 · 31 citations)
What has been tried
72 papers here report 476 measured changes (a component added, removed or swapped, compared with a baseline): helped 63%, no clear effect 8%, hurt 22%, mixed 8%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Scale the Myerson price by \nicefrac{2}{3} | Simulation settings tested · revenue | Helped | Pay to (Not) Play: Monetizing Impatience in Mobile Games (AAAI 2024 · 6 citations) | |
| Replace uniform thresholds with query-specific thresholds | G⟨4, 5, 1⟩ · number of added documents | three documents -> one document | Helped | On the Power of Strategic Corpus Enrichment in Content Creation Games (AAAI 2025 · 3 citations) |
| add the auxiliary task during engagement-model training | SPG · ACC | 0.708 -> 0.734 | Helped | EnMatch: Matchmaking for Better Player Engagement via Neural Combinatorial Optimization (AAAI 2024 · 3 citations) |
| Set β>0 rather than β=0 | Leduc poker · strategy deviation from standard CFR | Helped | Preference-CFR: Beyond Nash Equilibrium for Better Game Strategies (ICML 2025 · 0 citations) | |
| Use cyclic permutations instead of the adjacent-permutation vertex set, under the stated width assumption | Strictly convex games with \Width(W) \geq \frac{n\varsigma}{c_W} · sample complexity | O\RoundBr{\frac{n^{15} \log(n\delta^{-1}\varsigma^{-1})}{\varsigma^4}} -> O\RoundBr{\frac{n^{5}c_W^4 \log(n c_W \delta^{ | Helped | Learning the Expected Core of Strictly Convex Stochastic Cooperative Games (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 51 papers; from OpenAlex and the papers' affiliations).
- Carnegie Mellon University · 5 papers
- Technion - Israel Institute of Technology · 4 papers
- Tsinghua University · 3 papers
- Shanghai University of Finance and Economics · 3 papers
- University of Electronic Science and Technology of China · 2 papers
- University of Warwick · 2 papers
- Ben-Gurion University of the Negev · 2 papers
- Columbia University · 2 papers
- Google · 2 papers
- University of California, Berkeley · 2 papers
Use it
Download BibTeX of 40 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
- Zero-sum game learning dynamics (107 papers)
- Correlated equilibria in sequential games (86 papers)
- Equilibrium solvers for adversarial games (25 papers)
Elsewhere in the topic
- Fair division of indivisible goods (130 papers)
- Committee voting rules (120 papers)
- Matching markets and welfare (119 papers)
- Monotone submodular maximization (116 papers)
- Learned auction design (105 papers)
- Streaming submodular algorithms (73 papers)
- Submodular influence maximization (33 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).