JAIR

869 papers1,338 directions
The Journal of Artificial Intelligence Research (JAIR) is a venue covering a broad spectrum of artificial intelligence and machine learning research. Active since 2003, the journal publishes work that spans theoretical foundations and practical applications. Its scope includes multi-agent interactions, reinforcement learning, and the integration of symbolic logic with neural architectures. Research published in JAIR frequently addresses complex decision-making and strategic depth. Key areas of focus include modeling strategic depth in multi-agent systems, security games involving boundedly rational adversaries, and deceptive rationalization in large reasoning models. The venue also features work on decision-focused learning using differentiable optimization layers and neuro-symbolic architectures designed for sample-efficient learning. Beyond algorithmic development, the journal explores formalisms for quantifying contexts and temporality, as well as procedural and causal fairness in machine learning. Methodological contributions often involve pseudo-likelihood estimation for large graphical models and inconsistency-tolerant reasoning for knowledge bases. Prolific contributors to the venue include researchers such as Jeffrey S. Rosenschein, Joseph M. Barnby, and Alvaro Velasquez, reflecting a community focused on both formal rigor and the evolving challenges of modern AI systems.

Papers by Year

2026 43
2025 63
2024 54
2023 52
2022 75
2021 67
2020 43
2019 31
2018 42
2017 34
2016 37
2015 25
2014 38
2013 24
2012 21
2011 23
2010 18
2009 28
2008 25
2007 20
2006 16
2005 18
2004 16
2003 14
2002 17
2001 6
2000 7
1999 11
1998 4
1997 6
1996 5
1995 11
1994 4
1993 1

Top Research Directions

Research directions most represented by papers from this venue.

Strategyproof Resource Allocation Without Money 12
Managing Combinatorial Explosion in Automated Planning 11
Scaling State Space Search Under Memory Constraints 10
Parameterized Complexity in Computational Social Choice 9
Balancing Logical Expressivity and Computational Tractability 9
Computational Complexity as a Barrier to Election Manipulation 9
The Computational Intractability of Exact Probabilistic Inference 9
Fair Division of Indivisible Resources 8
Sample Efficient Reinforcement Learning 8
Taming the Complexity of Decentralized Multiagent Planning 8
Compressing Belief Spaces for Tractable Partially Observable Planning 8
Point Based Value Iteration for Partially Observable MDPs 7
Balancing Heuristic Accuracy and Computational Cost in Search 7
Scaling Symbolic Reasoning to Large Knowledge Bases 7
Decentralized Coordination Under Partial Observability 7

Top Authors

AuthorPapers
Joseph Halpern18
Moshe Tennenholtz16
Ian Horrocks10
Piotr Faliszewski10
Adnan Darwiche9
Alan Fern9
Bernardo Cuenca Grau9
Frank Hutter9
Milind Tambe9
Mirella Lapata8
Regina Barzilay8
Subbarao Kambhampati8
Carsten Lutz7
Joelle Pineau7
Kai Ming Ting7
Matthijs T. J. Spaan7
Michael J. Wooldridge7
Michael P. Wellman7
Thomas Eiter7
William Yeoh7

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Mean Field Theory for Sigmoid Belief Networks1996
On Partially Controlled Multi-Agent Systems1996
Reinforcement Learning: A Survey1996
Adaptive Load Balancing: A Study in Multi-Agent Learning1995
A Domain-Independent Algorithm for Plan Adaptation1995
Diffusion of Context and Credit Information in Markovian Models1995
FLECS: Planning with a Flexible Commitment Strategy1995
Learning Membership Functions in a Function-Based Object Recognition System1995
Pac-Learning Recursive Logic Programs: Efficient Algorithms1995
Pac-learning Recursive Logic Programs: Negative Results1995
Provably Bounded-Optimal Agents1995
Solving Multiclass Learning Problems via Error-Correcting Output Codes1995
Statistical Feature Combination for the Evaluation of Game Positions1995
Translating between Horn Representations and their Characteristic Models1995
Bias-Driven Revision of Logical Domain Theories1994
On Planning while Learning1994
Operations for Learning with Graphical Models1994
Random Worlds and Maximum Entropy1994
A Market-Oriented Programming Environment and its Application to Distributed Multicommodity Flow Problems1993

« prev Page 18/18