The original goal of the AI field was the construction of “thinking machines”, that is, computer systems with human-like general intelligence. For the last few decades, however, the majority of AI researchers have focused on what can be called “narrow AI” – systems with intelligence limited to specific, highly constrained tasks. In recent years more and more researchers have recognized the necessity – and feasibility – of returning to the original goals of the field. Increasingly, there is a call for confronting the more difficult issues of human-level intelligence, and more broadly “artificial general intelligence” (AGI).

Continuing the mission of the first three highly successful Conferences on Artificial General Intelligence, AGI-11 will gather an international group of leading academic and industry researchers involved in serious scientific and engineering work aimed directly at the goal of AGI. This is the only major conference series devoted wholly and specifically to the creation of AI systems possessing general intelligence at the human level and beyond.  AGI-11 will be hosted by Google in Mountain View, California.

Submit papers or proposals, for workshops, tutorials, or demos, electronically to EasyChair (you may need to Create an EasyChair Account first). Whether an accepted paper (either full-length or short position statement) will be presented as a talk or as a poster will be determined by the Program Committee, in part based on paper quality as assessed by the anonymous reviewers, and in part according to the extent the paper addresses a topic of core interest to the AGI community. All accepted papers are required to have at least one registered author per paper. Multiple papers require multiple registrations. AGI-11 will accept two types of submissions: full-length papers (10 pages) and short position statements (3 pages).

A good sense of the overall nature of the conference may be found via perusing AGI-10AGI-09, and AGI-08.

AGI-11 Notifications Sent!

Notifications have now been sent for all of the 100+ AGI-11 paper submissions. Thank you to everyone who participated – there were many excellent submissions this year. Acceptance rates were 27% for full papers, and 52% including poster papers. If you submitted a paper and not yet received notification, please contact us immediately. Accepted authors, please don’t forget to format your final submissions in accordance with the guidelines. A prefilled copyright form for AGI-11 may be found at Copyright Form.

Accepted Papers

Jianglong Nan and Fintan Costello A Demonstration of Combining Spatial and Temporal Perception
Bas Steunebrink and Jürgen Schmidhuber A Family of Gödel Machine Implementations
Joscha Bach A Motivational System for Cognitive AI
Randal Koene AGI and Neuroscience: Open Sourcing the Brain
Andras Lorincz and Daniel Takacs AGI Architecture Measures Human Parameters and Optimizes Human Performance
Samuel Epstein and Margrit Betke An Information Theoretic Representation of Agent Dynamics as Set Intersections
Andrew Coward Brain anatomy and artificial intelligence
Tom Schaul, Leo Pape, Tobias Glasmachers, Vincent Graziano and Juergen Schmidhuber Coherence Progress: A Measure of Interestingness Based on Fixed Compressors
Javier Insa-Cabrera, David L. Dowe, Sergio España-Cubillo, M.Victoria Hernandez-Lloreda and Jose Hernandez-Orallo Comparing humans and AI agents
Eliezer Yudkowsky Complex Value Systems are Required to Realize Valuable Futures
David L. Dowe, Jose Hernandez-Orallo and Paramjit K. Das Compression and intelligence: social environments and communication
Serge Thill Considerations for a neuroscience-inspired approach to the design of artificial intelligent systems
Mark Ring and Laurent Orseau Delusion, Survival, and Intelligent Agents
Alessandro Oltramari and Christian Lebiere Extending Cognitive Architectures with Semantic Resources
Paul Rosenbloom From Memory to Problem Solving: Mechanism Reuse in a Graphical Cognitive Architecture
Marius Raab, Mark Wernsdorfer, Emanuel Kitzelmann and Ute Schmid From Sensorimotor Maps to Rules: An Agent Learns from a Stream of Experience
Brian Mingus, Trent Kriete, Seth Herd, Dean Wyatte, Kenneth Latimer and Randy O’Reilly Generalization of Figure-Ground Segmentation from Binocular to Monocular Vision in an Embodied Biological Brain Model
Ben Goertzel Imprecise Probability as a Linking Mechanism Between Deep Learning, Symbolic Cognition and Local Feature Detection in Vision Processing
Pedro Ortega and Daniel Braun Information, Utility & Bounded Rationality
Unmesh Kurup, Christian Lebiere and Anthony Stentz Integrating Perception and Action for AGI
Haris Dindo, Antonio Chella, Giuseppe La Tona, Monica Vitali, Eric Nivel and Kristinn R. Thorisson Learning Problem Solving Skills from Demonstration: An Architectural Approach
Andras Lorincz Learning the States of Markov Decision Processes: A Brain Inspired Neural Model
Daniel Dewey Learning What to Value
Daniel Silver Machine Lifelong Learning: Challenges and Benefits for Artificial General Intelligence
Bill Hibbard Measuring Agent Intelligence via Hierarchies of Environments
Karol Walędzik and Jacek Mańdziuk Multigame playing by means of UCT enhanced with automatically generated evaluation functions
Matthew Ikle and Ben Goertzel Nonlinear-Dynamical Attention Allocation via Information Geometry
Juergen Schmidhuber, Dan Ciresan, Ueli Meier, Jonathan Masci and Alex Graves On Fast Deep Nets for AGI Vision
Jose Hernandez-Orallo, David L. Dowe, Sergio España-Cubillo, M.Victoria Hernandez-Lloreda and Javier Insa-Cabrera On more realistic environment distributions for defining, evaluating and developing intelligence
Zhenhua Cai, Ben Goertzel and Nil Geisweiller OpenPsi: Realizing Dorner’s ”Psi” Cognitive Model in the OpenCog Integrative AGI Architecture
Tobias Glasmachers and Jürgen Schmidhuber Optimal Direct Policy Search
Iris Oved and Ian Fasel Philosophically Inspired Concept Acquisition for Artificial General Intelligence
Yi Sun, Faustino Gomez and Juergen Schmidhuber Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments
Mark Waser Rational Universal Benevolence: Simpler, Safer, and Wiser than “Friendly AI”
Helmar Gust, Ulf Krumnack, Maricarmen Martinez, Ahmed Abdel-Fattah, Martin Schmidt and Kai-Uwe Kuehnberger Rationality and General Intelligence
Leo Pape and Arthur Kok Real-world Limits to Algorithmic Intelligence
Pei Wang and Seemal Awan Reasoning in Non-Axiomatic Logic: A Case Study in Medical Diagnosis
Pedro Alejandro Ortega, Daniel Alexander Braun and Simon Godsill Reinforcement Learning and the Bayesian Control Rule
Laurent Orseau and Mark Ring Self-Modification and Mortality in Artificial Agents
Linus Gisslen, Matt Luciw, Vincent Graziano and Jürgen Schmidhuber Sequential Constant Size Compressors and Reinforcement Learning
Bill Hibbard Societies of Intelligent Agents
Sergio Pissanetzky Structural Emergence in Partially Ordered Sets is the Key to Intelligence
Derek Monner and James Reggia Systematically Grounding Language through Vision in a Deep, Recurrent Neural Network
Eray Ozkural Teraflop-scale Incremental Machine Learning
Benjamin Johnston The Collection of Physical Knowledge and its Application in Intelligent Systems
Claude Touzet The Illusion of Internal Joy
Javier Snaider, Ryan Mccall and Stan Franklin The LIDA Framework as a General Tool for AGI
Ben Goertzel and Matthew Ikle Three Hypotheses About the Geometry of Mind
Elias Ruiz, Augusto Melendez and Enrique Sucar Towards a General Vision System based on Symbol-Relation Grammars and Bayesian Networks
Florin Popescu Wagging the dog: human vs. machine inference of causality in visual sequences
Janelle Szary, Bryan Kerster and Christopher Kello What Makes a Brain Smart? Reservoir Computing as an Approach for General Intelligence

Author Instructions

Submissions should follow the Spring Lecture Notes in Artificial Intelligence author instructions here.  The MS Word 2007 templates may be downloaded here also.

Important Dates

Final Submissions – Due 1st of March (extended from 15th of February), 2011 Notification Date – Due 26th of April

AGI-11 Submissions Policy

Whether an accepted paper (of either length) will be presented as a talk or as a poster will be determined by the Program Committee, in part based on paper quality as assessed by the anonymous reviewers, and in part according to the extent the paper addresses a topic of core interest to the AGI community. The acceptance of a paper is based on the assumption that one of the authors will attend the conference to present the paper. Any questions can be directed to one of the conference chairs.

AGI-11 Copyright Policy

Springer-Verlag will hold the copyright to the published paper. Authors should archive their paper on their own web site as well, with the following text included: “The original publication is available at”. The Springer Lecture Notes in Artificial Intelligence copyright form is available here.

The AGI conference will be part of Springer Lecture Notes in Artificial Intelligence (LNAI). This subseries is devoted to the publication of state-of-the-art research results in artificial intelligence, at a high level and in both printed and electronic versions. The topics in LNAI include automated reasoning, automated programming, algorithms, knowledge representation, agent-based systems, intelligent systems, expert systems, machine learning, natural-language processing, machine vision, robotics, search systems, knowledge discovery, data mining, and related programming languages.