AAMAS 2027 - Call for Papers

---

Submission Instructions (Main Technical Track)

Important Dates

Author registration on OpenReview: 17 Sep 2026

• Abstract submission: 1 Oct 2026

• Paper submission: 8 Oct 2026

• Rebuttal period: 20 - 24 Nov 2026

• Author notification: 21 Dec 2026

• Camera-ready paper: 25 Jan 2027

• Conference: 3 - 7 May 2027

All deadlines are at the end of the specified day, Anywhere on Earth (UTC-12).

For queries related to submission, please contact aamas2027pcs@gmail.com.

For responses to questions frequently asked by authors who wish to submit to AAMAS, a FAQ page will be posted here soon.

Reciprocal reviewer policy: To ensure a fair distribution of reviewing load and maintain high review quality, AAMAS has introduced a Reciprocal Reviewer Policy.

 

Areas of Interest

We welcome technical papers describing significant and original research on all aspects of the theory and practice of autonomous agents and multiagent systems, spanning established areas as well as emerging topics such as generative and agentic AI. If you are new to this community, then we encourage you to consult the proceedings of previous editions of the conference to fully appreciate the scope of AAMAS. At the time of submission, you will be asked to associate your paper with one of the following areas of interest:

• Learning and Adaptation (LEARN)

• Generative and Agentic AI (GAAI)

• Game Theory and Economic Paradigms (GTEP)

• Coordination, Organizations, Institutions, Norms, and Ethics (COINE)

• Search, Optimization, Planning, and Scheduling (SOPS)

• Representation, and Reasoning (RR)

• Engineering and Analysis of Multiagent Systems (EMAS)

• Modelling and Simulation of Societies (SIM)

• Human-Agent Interaction (HAI)

• Robotics and Control (ROBOT)

• Innovative Applications and Societal Impact (IASI)

Additionally, AAMAS 2027 includes several special tracks. You can find more information about these tracks here [link].

Learning and Adaptation (LEARN)

Area Chairs: Stefano Albrecht, Ivana Dusparic, Akshat Kumar, Leandro Marcolino, Stefano Mariani, Pradeep Varakantham, Yaodong Yang, Chongjie Zhang

Topics:

• Reasoning and learning under uncertainty

• Supervised learning

• Unsupervised and representation learning

• Reinforcement learning

• Multiagent learning

• Evolutionary and biologically inspired algorithms

• Learning agent capabilities

• Learning agent-to-agent interactions, including learning to communicate and emergent communication

• Human-in-the-loop learning

• Few-shot learning

• Distributionally robust learning

• Adversarial learning

• Imitation learning

Description:

This area welcomes papers whose primary contribution concerns learning and adaptation in single-agent or multiagent systems. Relevant submissions include theoretical, algorithmic, and empirical work on supervised, unsupervised, reinforcement, imitation, evolutionary, adversarial, robust, and human-in-the-loop learning, as well as learning agent capabilities and agent-to-agent interactions.

Papers should be submitted to LEARN when the main contribution is a learning method, learning-theoretic analysis, or empirical study of learning in agent or multiagent settings. Papers focused primarily on generative-model-based agent architectures, workflows, or evaluation should be submitted to GAAI.

Generative and Agentic AI (GAAI)

Area Chairs: Bo An, Giovanni Ciatto, Amit Chopra, Yali Du, Andrei Olaru, Eugene Vorobeychik, Weinan Zhang

Topics:

• Memory, state, context, long-lived interaction, and other architectural patterns for generative and agentic AI systems

• Orchestration and workflows of agents and tools

• Runtime support, infrastructure, and engineering for generative and agentic AI systems

• Embodied, multimodal, and grounded generative AI agents

• Open-ended, autonomous, and self-improving agents based on generative AI

• Planning, reasoning, and long-horizon agentic workflows

• Agency and learning in generative and agentic AI

• Interaction protocols for agentic AI

• Coordination, cooperation, and negotiation in generative AI agents

• Normative reasoning and institutional constraints for generative AI agents

• Theory of mind, user modeling, and social reasoning in generative AI agents

• Hybrid classic-generative agents, with a focus on how generative AI agents use classical tools, models, and protocols

• Failure handling, recovery, and resilience in agentic AI

• Modeling and analysis of generative AI agents

• Instruction following and multi-turn agent behavior in generative AI agents

• Human-agent interaction for delegation, feedback, and task collaboration in generative AI agents

• Agentic decision support and decision boundaries

• Alignment, learning from human feedback, and controllability of generative and agentic AI systems

• Explainability, introspection, and debugging for generative AI agents and systems

• Assurance, verification, and safety in generative and agentic AI systems

• Benchmarks, evaluation, and metrics for generative and agentic AI systems

• Generative AI-supported specification and implementation of agents and multiagent systems

• Agentic AI applications in science, software, education, and critical domains

Description:

This area welcomes papers whose primary contribution advances generative and agentic AI systems, namely agents or multiagent systems that act, reason, interact, coordinate, or make decisions by using, integrating, or analyzing generative AI models. Relevant submissions may address foundations, architectures, learning methods, orchestration, tool use, evaluation, safety, alignment, verification, governance, deployment, and human-agent or multiagent interaction in generative-agent systems.

Papers should be submitted to GAAI when the central technical contribution concerns agents whose capabilities, architecture, reasoning, interaction, learning, evaluation, or deployment substantially rely on generative AI models. Papers whose main contribution is a general learning, planning, engineering, governance, or human-interaction method should instead be submitted to the corresponding AAMAS area, unless the generative-agent aspect is central.

Submissions where the core contribution is not specifically about agents or multiagent systems are out of scope. Advances in language models, prompt engineering, generic tool use, or arbitrary generative tasks are outside the scope of this area unless they make a clear contribution to autonomous agents or multiagent systems.

Game Theory and Economic Paradigms (GTEP)

Area Chairs: Haris Aziz, Branislav Bosansky, Vincent Conitzer, Christopher Kiekintveld, Villiam Lisy, Pinyan Lu, Thanh Nguyen, Haifeng Xu, Dengji Zhao

Topics:

• Auctions and mechanism design

• Economic foundations and market design for economics of AI agents

• Bargaining and negotiation

• Behavioural game theory

• Evolutionary game theory

• Non-cooperative games: equilibrium concepts

• Non-cooperative games: computational issues

• Non-cooperative games: theory and applications

• Voting and preference aggregation

• Social choice and social networks

• Judgment aggregation and forecasting

• Fair allocation and matching

• Tournaments and agent evaluation

• Digital and liquid democracy

• Strategic coalition formation

• Cooperative games

• Persuasion and information design

Description:

This area welcomes papers whose primary contribution advances game theory, economic paradigms, mechanism design, market design, social choice, or strategic decision-making for agents and multiagent systems. Relevant submissions include theoretical, computational, and applied work on cooperative and non-cooperative games, equilibrium computation, auctions, bargaining, negotiation, voting, allocation, matching, persuasion, information design, and economic models of AI agents.

Papers should be submitted to GTEP when the strategic, economic, game-theoretic, or social-choice model is central to the contribution. Papers focused mainly on norms, institutions, ethics, or organizational governance should be submitted to COINE unless the strategic or economic model is central.

Coordination, Organizations, Institutions, Norms, and Ethics (COINE)

Area Chairs: Pradeep K. Murukannaiah, Vahid Yazdanpanah

Topics:

• Coordination and teamwork

• Social network analysis

• Norms and normative systems

• Multiagent organizations and institutions

• Non-strategic coalition or team formation

• Communication, including communication using natural language

• Policy, regulation, and accountability

• Safety, robustness, trust, and reputation

• Ethical considerations, including bias, equity, fairness, privacy, safety, security, and transparency

• Values and preferences

• Agreement technologies: negotiation and argumentation

• Responsible socio-technical systems

• Explainability and interpretability of norms and ethics in human-agent teams

• Ethical and governance challenges of LLM-based agents in coordination, organizations, institutions, and normative systems

• Rebellion and disobedience in AI

Description:

This area welcomes papers whose primary contribution concerns coordination, organizations, institutions, norms, ethics, accountability, governance, and responsible behavior in agent and multiagent systems. Relevant submissions include theoretical, computational, empirical, and design-oriented work on teamwork, social reasoning, normative systems, institutions, trust, reputation, values, policy, regulation, agreement technologies, and responsible socio-technical systems.

Research in agent and multiagent systems has a long history of balancing agent autonomy, adaptation, and distributed social reasoning with system-level considerations such as organizational and institutional policy enforcement, safety, security, fairness, and accountability. Submissions may address machine-machine cooperation, human-machine cooperation, and multiagent coordination, especially where these raise questions of transparency, trust, responsibility, governance, or alignment with social norms and ethical values.

Papers should be submitted to COINE when social, institutional, normative, organizational, governance, or ethical dimensions are central to the contribution. Papers focused primarily on human-subject interaction design or evaluation should be submitted to HAI; papers focused primarily on generative-agent architectures should be submitted to GAAI.

Search, Optimization, Planning, and Scheduling (SOPS)

Area Chairs: Prashant Doshi, Sarah Keren, Stefania Monica, Felipe Meneguzzi, Roni Stern, Nathan Sturtevant

Topics:

• Single-agent planning and scheduling

• Multiagent planning and scheduling

• Decentralized planning and scheduling

• Planning under uncertainty

• Decision-theoretic planning

• Temporal reasoning and scheduling

• Combinatorial optimization

• Constraint programming

• Distributed constraint reasoning

• Resource and task allocation

• Non-strategic coalition formation

• Plan and goal recognition

• Human-aware planning and scheduling

• Knowledge representation methods for search, optimization, planning, and scheduling

Description:

This area welcomes theoretical and experimental contributions to search, optimization, planning, and scheduling in single-agent and multiagent systems. Relevant submissions include decentralized planning, planning under uncertainty, decision-theoretic planning, temporal reasoning and scheduling, combinatorial optimization, constraint programming, distributed constraint reasoning, resource and task allocation, plan and goal recognition, human-aware planning and scheduling, and non-strategic coalition formation.

Contributions that integrate learning-based methods, including foundation models, with search, optimization, planning, and scheduling techniques are welcome, provided that the primary contribution remains in the SOPS area. Similarly, approaches to motion and path planning are relevant when they are framed as planning, search, or decision-making problems for autonomous agents or multiagent systems.

Papers should be submitted to SOPS when the primary contribution is a search, optimization, planning, scheduling, or decision-theoretic method, even if the method is applied to multiagent, robotic, human-aware, or foundation-model-assisted settings.

Representation and Reasoning (RR)

Area Chairs: Yves Lesperance, Ken Satoh, Tran Cao Son

Topics:

• Neurosymbolic approaches

• Argumentation

• Agent theories and models

• Explainability

• Logics for agent reasoning

• Ontologies for agents

• Reasoning about knowledge, beliefs, goals, actions, plans, and change in multiagent systems

• Reasoning and problem solving in agent-based systems

• Verification of agents and multiagent systems

• Autoformalization

• Logic-constrained learning

• Strategic reasoning and strategy logics

Description:

This area welcomes theoretical and experimental contributions to knowledge representation and reasoning for single-agent and multiagent systems. Relevant submissions include formal and computational approaches to agent theories, logics for agent reasoning, argumentation, ontologies, knowledge graphs, semantic frameworks, strategic reasoning, reasoning about knowledge, beliefs, goals, actions, plans, and change, verification, autoformalization, logic-constrained learning, and neurosymbolic reasoning.

Knowledge representation is interpreted broadly, encompassing formal approaches such as epistemic, strategic, and description logics, as well as data-driven techniques such as representation learning, when they support reasoning in agent or multiagent systems. Relevant reasoning paradigms include automated reasoning, theorem proving, verification-based approaches, probabilistic inference, neurosymbolic methods, and reasoning methods that support trustworthiness, accountability, transparency, fairness, explainability, or responsible AI.

Papers should be submitted to RR when the primary contribution is a representation or reasoning framework, method, analysis, or formalism for agents or multiagent systems. Papers whose primary contribution is planning, scheduling, or optimization should be submitted to SOPS, unless the representation or reasoning formalism is central.

Engineering and Analysis of Multiagent Systems (EMAS)

Area Chairs: Rem Collier, Roberto Micalizio, Sebastian Rodriguez

Topics:

• Requirements capture and formal specification of multiagent systems

• Programming paradigms and languages for autonomous agents

• Runtime infrastructures and deployment platforms for scalable MAS, including cloud, edge, and hybrid settings

• Testing, debugging, verification, validation, certification, and DevOps for multiagent systems

• Scalability, fault tolerance, and performance engineering of MAS platforms

• Engineering self-adaptive agents, including lifecycle management, continuous evolution, and deployment pipelines

• Interoperability, business agreements, and agent-to-agent protocols

• Declarative, logic-based, and BDI agent programming and architectures

• Engineering MAS-based simulations for rigorous analysis and experimentation

• Sociotechnical governance tools for norms, ethics, and accountability

• Human-centered engineering for usability, transparency, and explainability

• Open-source toolchains, benchmarks, and reproducible MAS testbeds

• Engineering learning agents, including platform design and online adaptation

• Engineering MAS with LLM methods

• Hybrid symbolic-subsymbolic agent systems, including engineering architectures and platforms for neurosymbolic reasoning

• Benchmarks, evaluation methodologies, and reproducible workflows for MAS

• Data-driven engineering processes for design, testing, and adaptation of agent systems

• Engineering MAS-based autonomous systems

Description:

This area welcomes papers whose primary contribution advances the engineering and analysis of agents and multiagent systems. Relevant submissions include work on software abstractions, programming languages, methodologies, architectures, runtime infrastructures, deployment platforms, testing, debugging, verification, validation, certification, monitoring, interoperability, scalability, reproducibility, and lifecycle management.

Papers integrating symbolic reasoning, learning, LLM-based components, or neurosymbolic methods are welcome when the focus is on engineering challenges and solutions. The area also welcomes contributions on engineering agent and multiagent systems whose behaviour, decisions, interactions, and failures are understandable to human users. This includes methods and tools for designing transparency into agent architectures, tracing and auditing agent behaviour, generating explanations of individual or collective decisions, monitoring compliance with requirements and norms, and supporting accountability in deployed systems.

Papers should be submitted to EMAS when the primary contribution concerns methods, tools, languages, platforms, infrastructures, or processes for engineering, deploying, testing, validating, maintaining, or analyzing agent and multiagent systems. Papers in which LLMs or other AI technologies perform the primary task while MAS engineering plays only a background role should be submitted to another area.

Modeling and Simulation of Artificial Societies (SIM)

Area Chairs: Paul Davidsson, Önder Gürcan, Takayuki Ito

Topics:

• Modeling for agent-based simulation

• Simulation of complex systems

• Modeling of societies and social simulations

• Agent-based modeling and evaluation of public policies

• Simulation techniques, tools, and platforms

• Analysis of agent-based simulations

• Calibration, verification, and validation of agent-based simulation systems

• Robustness, reliability, and trustworthiness of agent-based simulations

• Design and implementation of large-scale agent-based simulations

• High-performance computing and frameworks for agent-based simulation

• Interactive and participatory simulation

• LLM-supported agent-based simulation and modeling

Description:

This area welcomes papers whose primary contribution concerns agent-based modeling and simulation of artificial societies and complex systems. Relevant submissions include modeling methods, simulation techniques, tools and platforms, calibration, verification, validation, robustness, participatory simulation, large-scale simulation, and the analysis of emergent behavior in social, organizational, economic, ecological, transportation, and socio-technical systems.

Artificial societies are computer simulations or models created to emulate and study the behavior of complex social systems. Agent-based models provide a way to analyze how individual behaviors, interactions, incentives, policies, and interventions give rise to emergent structures and dynamics at the system level. Relevant application areas include ecology, biology, economics, transportation, management, organizational studies, and the social sciences.

Papers should be submitted to SIM when simulation is central to the contribution, either as a methodological advance or as a way to explain, predict, explore, or evaluate complex systems.

Human-Agent Interaction (HAI)

Area Chairs: Reuth Mirsky, Sarath Sreedharan

Topics:

• Human-agent interaction

• Agent-based analysis of human interactions

• Socially interactive agents

• Trust and explainability in human-agent interactions

• Human-robot interaction and collaboration

• Social robotics and social interactions

• Mixed-initiative and shared autonomy in human-agent interactions

• Groups of humans and agents

• Agent models and architectures for interaction with humans

• Design for human-agent interaction

• Virtual humans

• Theory of mind and user modeling in human-agent interaction

• Modelling, detecting, and accounting for deception in human-AI teams

• Human cognitive modeling for agent interaction

Description:

This area welcomes papers whose primary contribution concerns the design, modeling, evaluation, or analysis of interaction between humans and agents. Relevant submissions include work on human-agent interaction, socially interactive agents, human-robot interaction, mixed-initiative and shared autonomy, groups of humans and agents, trust, explainability, deception, theory of mind, cognitive modeling, virtual humans, and agent architectures for interaction with humans.

Human interaction with artificially intelligent agents is becoming increasingly common in the social and organizational contexts through which people make decisions, coordinate work, and act in the world. Significant challenges arise when moving from purely multiagent systems to hybrid systems that incorporate bidirectional human-agent interaction in competitive, cooperative, or mixed settings. Agents need models and architectures that support perception and recognition of human states and activities, interaction modalities that enable coordination, and careful consideration of human factors and ethical concerns.

Papers should be submitted to HAI when human-agent interaction is central to the research question, methodology, or evaluation. Papers focused primarily on institutional, normative, or governance aspects should be submitted to COINE; papers focused primarily on generative-agent architectures should be submitted to GAAI.

Robotics and Control (ROBOT)

Area Chairs: Chris Amato, Sven Koenig, Peter Stone

Topics:

• Coordination and collaboration in robotic systems

• Swarm and multi-robot collective behavior

• Robots in adversarial settings

• Perception and vision for autonomous robots

• Networked systems and distributed robotics

• Foundation models for autonomous robots and robot teams

• Knowledge representation and reasoning in robotic systems

• Robot planning and decision-making

• Mapping, localization, and navigation for autonomous robots and robot teams

• Autonomous robot manipulation and task execution

• Decision-making and control for autonomous robots and robot teams

• Robot learning for autonomy and adaptation

• Long-term or lifelong autonomy for robotic systems

• Execution monitoring and failure recovery for robots

• Robot modeling and simulation for autonomous agents

• Explainability, trust, and ethics for robots

• Hybrid systems of robots with humans and/or software agents

Description:

This area welcomes papers whose primary contribution concerns autonomous robots, robotic agents, multi-robot systems, or the interaction of robots with humans, software agents, or physical environments. Relevant submissions include work on coordination, collaboration, swarms, distributed robotics, robot planning, robot learning, knowledge representation and reasoning for robots, long-term autonomy, execution monitoring, failure recovery, modeling and simulation, explainability, trust, ethics, decision-making, and control for autonomous robots.

Robots are embodied and situated agents that operate in the physical world. Research on autonomous agents and multiagent systems shares many challenges and synergies with intelligent robotics, especially where robotic systems must reason, learn, plan, coordinate, adapt, or act autonomously in realistic settings.

Submissions involving perception, vision, mapping, localization, manipulation, or control are welcome when these components are integrated into, or make a clear contribution to, autonomous robots or multi-robot systems.

Innovative Applications and Societal Impact (IASI)

Area Chairs: Georgina Curto, Stéphane Galland, Alessandro Ricci

Topics:

• Deployed or emerging applications of agent-based and agentic systems addressing real-world challenges

• Agent-based and agentic systems for social good, sustainability, public policy, education, health, science, industry, and critical domains

• Realistic agent-based and agentic models of human organizations, institutions, and socio-technical systems

• Evaluation of the cognitive, social, organizational, or decision-support capabilities of agent-based and agentic systems in real-world settings

• Integration of agent-based and agentic systems with other AI, software, cyber-physical, robotic, simulation, or decision-support technologies

• Hybrid agent-based, agentic AI, and reinforcement learning solutions for real-world applications

• Deployment, adoption, usability, robustness, safety, and maintainability of agent-based and agentic technologies in practice

• Challenges, best practices, and lessons learned from real-world deployments of agent-based and agentic technologies

• Evaluation methodologies, benchmarks, and evidence of measurable impact for innovative applications

• Stakeholder involvement, participatory design, and co-creation of agent-based and agentic applications

• Ethical, legal, societal, and environmental implications of deployed or emerging agent-based and agentic systems

• Frameworks, platforms, and tools supporting the implementation and deployment of innovative agent-based and agentic applications

Description:
This area welcomes papers whose primary contribution is an innovative application or demonstrated societal impact of agent technologies. Relevant submissions include deployed systems, emerging applications, realistic prototypes, stakeholder-driven designs, and rigorous evaluations of autonomous agents and multiagent systems addressing real-world challenges.

Submissions should clearly explain the application context, the role of agents, the novelty of the application, and the evidence of benefit, feasibility, adoption, or measurable impact. Collaborations with relevant stakeholders are strongly encouraged, especially where they demonstrate that the proposed approach addresses a real need and can be used, evaluated, or deployed in practice.

Papers should be submitted to IASI when the primary contribution is an innovative application, deployment, realistic validation, stakeholder-driven design, or demonstrated societal impact of agent-based or agentic technologies. Papers whose primary contribution is a new algorithm, architecture, learning method, engineering tool, or simulation method should be submitted to the corresponding technical area unless the application or impact contribution is central.

For submission instructions, see here.

All submissions will be rigorously peer-reviewed and evaluated on the basis of the overall quality of their technical contribution, taking into account criteria such as originality, significance, soundness, reproducibility, clarity, relevance to the conference, quality of presentation, as well as understanding and appropriate referencing of the state of the art. Papers may be moved to a different area based on fit but may be desk rejected if deemed out of scope.

Papers submitted to AAMAS 2027 could be selected for publication in the Proceedings of AAMAS 2027 under a CC-BY licence. Papers that are not selected will be automatically considered for publication in the Findings of AAMAS 2027 under a CC-BY licence, unless the authors opt out of this option in the submission form (see more information about AAMAS 2027 Findings here). Papers selected for publication in the Proceedings and papers selected for publication in the Findings have the same length and follow the same submission format. Papers that are not selected for either will be rejected.