Opponent Modeling

Ask about this topic

Overview

Opponent modeling asks how an agent can infer what others know, want, or are likely to do from their behavior, especially when intentions and states are only partly observable. Methods include Bayesian belief tracking, sequence models and transformers, causal and intent representations, imitation learning, and reinforcement-learning policies that choose among opponent-specific responses. These approaches are tested in settings such as negotiation, poker, multi-agent navigation, pursuit-evasion, and repeated games, where predictions can support cooperation, adaptation, or strategic exploitation. A central challenge is that accurate predictions or reported beliefs do not always lead to better decisions, while exploiting weak opponents must be balanced against robustness to unfamiliar or near-equilibrium play.

Latest papers

CardsList

17 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

  1. Game-Theoretic Solvers with Bayesian Opponent Modeling and Moral Rhetoric Framing for GLEE

    Oct 27, 2026Hayden ArnoldMulti-Agent NegotiationOpponent Modeling

    KAIST

  2. When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial Observability

    Oct 13, 2026Marcel Petran, Stefan EdelkampOpponent ModelingMulti-Agent Reinforcement Learning

    Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic

  3. Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models

    Oct 12, 2026Hanbo Xie, Yue Zhao, Robert C. WilsonOpponent ModelingTheory of Mind

    University of Sussex

  4. Orchestrating Level-KK Policies Against Unknown Opponents in Partially-Observable Dynamic Games

    Oct 4, 2026Addison Kalanther, Sanika Bharvirkar, Daniel Bostwick +2Multi-Agent OrchestrationMulti-Agent Reinforcement Learning

    EECS, University of California, Berkeley, CA, USA · ECE, Johns Hopkins University, Baltimore, MD, USA

  5. Hierarchical Belief Modeling for Zero-Shot Opponent Adaptation in Partially Observable Multi-Agent Navigation

    Sep 11, 2026Kowei Shih, Lu Cheng, Zeyu Wang +2Opponent ModelingPartially Observable RL

    Tsinghua University, Beijing, China · Stevens Institute of Technology, New Jersey, USA · University of California, Los Angeles, Los Angeles, USA +2

  6. RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

    Jun 24, 2026Babak Rahmani, Sebastian Dziadzio, Joschka Strüber +2Opponent ModelingLLM-Based Program Synthesis

    Tübingen AI Center

  7. Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents

    Jun 16, 2026Ankita Samaddar, Sandeep Neema, Daniel Balasubramanian +1Opponent ModelingAutonomous Cyber Defense

    Departmaent of Computer Science Vanderbilt University Nashville, TN

  8. Enhancing the MADDPG Algorithm for Multi-Agent Learning via Action Inference and Importance Sampling

    Jun 3, 2026Marc Walden, Jason Liu, Shaashwath Sivakumar +2Opponent ModelingImportance Sampling

    Department of Mathematics, University of California Los Angeles, Los Angeles, CA, USA

  9. Generalized Intention Modeling in Multi-Agent Reinforcement Learning

    May 29, 2026Mateusz Odrowaz-Sypniewski, Jasmine Bayrooti, Ajay Shankar +1Opponent ModelingMulti-Agent Reasoning

    Department of Computer Science and Technology, University of Cambridge, UK

  10. AlphaExploitem: Going Beyond the Nash Equilibrium in Poker by Learning to Exploit Suboptimal Play

    May 9, 2026Vlad Murgoci, Matthijs Spaan, Yaniv OrenOpponent ModelingGame-Playing Agents

    Delft University of Technology · CD Delft, The Netherlands · Department of Intelligent Systems

  11. SOM: Structured Opponent Modeling for LLM-based Agents via Structural Causal Model

    May 8, 2026Shiyue Cao, Pei Xu, Likun Yang +3Opponent ModelingMulti-Agent Reasoning

    School of Artificial Intelligence, University of Chinese Academy of Sciences & Institute of Automation, Chinese Academy of Sciences Beijing, China · National Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences Beijing, China +1

  12. Distilling Bayesian Belief States into Language Models for Auditable Negotiation

    May 6, 2026Zongqi Cui, Baihan LinMulti-Agent NegotiationOpponent Modeling

    Emory University · Icahn School of Medicine at Mount Sinai

  13. StratFormer: Adaptive Opponent Modeling and Exploitation in Imperfect-Information Games

    Apr 28, 2026Andy Caen, Mark H. M. Winands, Dennis J. N. J. SoemersOpponent ModelingGame-Playing Agents

    Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands

  14. Preference Estimation via Opponent Modeling in Multi-Agent Negotiation

    Apr 17, 2026Yuta Konishi, Kento Yamamoto, Eisuke Sonomoto +8Multi-Agent NegotiationOpponent Modeling

    1Graduate School of Informatics, Kyoto University, Kyoto, Japan · 2Accenture Japan Ltd, Tokyo, Japan

  15. Opponent State Inference Under Partial Observability: An HMM-POMDP Framework for 2026 Formula 1 Energy Strategy

    Mar 1, 2026Kalliopi KleisarchakiPartially Observable Stochastic GamesOpponent Modeling

    Independent Researcher

  16. Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation

    Feb 22, 2026Xiangyu Liu, Di Wang, Zhe Feng +1Repeated GamesMulti-Agent Negotiation

    Google Research · University of Maryland, College Park

  17. Multi-agent cooperation through in-context co-player inference

    Feb 18, 2026Marissa A. Weis, Maciej Wołczyk, Rajai Nasser +4Cooperative MARLDecentralized MARL

    Google, Paradigms of Intelligence Team · Santa Fe Institute