Research map / Multi-agent systems and games / Games and equilibria
Learning with strategic agents
Designs contracts, menus, and mechanisms for learning in principal-agent and strategic interactions.
74 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 Checklist 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.
22 papers in 2023–24 and 25 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 17.3% to 17.5%.
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 · Learning Market Parameters Using Aggregate Demand Queries (AAAI 2016 · 4 citations)
- 2019 · Learning to Collaborate in Markov Decision Processes (ICML 2019 · 13 citations)
- 2020 · Reinforcement Mechanism Design: With Applications to Dynamic Pricing in Sponsored Search Auctions (AAAI 2020 · 39 citations)
- 2021 · Signaling in Bayesian Network Congestion Games: the Subtle Power of Symmetry (AAAI 2021 · 33 citations)
- 2022 · Path-Specific Objectives for Safer Agent Incentives (AAAI 2022 · 11 citations)
- 2023 · Formal Verification of Bayesian Mechanisms (AAAI 2023 · 4 citations)
- 2024 · Contracting with a Learning Agent (NeurIPS 2024 · 5 citations)
- 2025 · Every Bit Helps: Achieving the Optimal Distortion with a Few Queries (AAAI 2025 · 2 citations)
- 2026 · Fairness Aware Reinforcement Learning via Proximal Policy Optimization (AAAI 2026 · 2 citations)
Earliest papers here
- Learning Market Parameters Using Aggregate Demand Queries (AAAI 2016 · 4 citations)
- Learning to Collaborate in Markov Decision Processes (ICML 2019 · 13 citations)
- Robust Multi-agent Counterfactual Prediction (NeurIPS 2019 · 7 citations)
What has been tried
45 papers here report 324 measured changes (a component added, removed or swapped, compared with a baseline): helped 59%, no clear effect 9%, hurt 24%, 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 |
|---|---|---|---|---|
| Restrict the endpoints from getting too close to the obstacle (TwoExtremeRestrict) | Maximum cost (L=0) · approximation ratio | \frac{2}{1+k} -> 2\cdot \max\left(\frac{1-(1-k)c}{1\!+\!k\!-(1-k)c}, \frac{k(2c-c^2)+1-c^2}{2-2c+2ck}, \frac{1+2ck}{2\! | Helped | Mechanism Design for Connecting Regions Under Disruptions (AAAI 2025 · 0 citations) |
| Vary the no-conflict weighting factor beta; use a value between 0.7 and 0.8 | Harvest · GeoMean | Mixed | Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment (NeurIPS 2025 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 16 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- Cleanup · 2 of 16 papers
Baselines
- Ind · 2 of 16 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 47 papers; from OpenAlex and the papers' affiliations).
- Carnegie Mellon University · 4 papers
- University of California, Berkeley · 3 papers
- University of Nebraska-Lincoln · 2 papers
- University of Oxford · 2 papers
- Polytechnic Institute of Milan · 2 papers
- Politecnico di Milano · 2 papers
- Huawei · 2 papers
- University of Wisconsin - Madison · 2 papers
- Google · 2 papers
Use it
Download BibTeX of 37 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)
- Strategic classification (51 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).