AAAI 2025 accepted papers on Multi-agent systems and games
140 of the 3,486 papers accepted at AAAI 2025 (4.0%) are on Multi-agent systems and games, compared with 3.2% at AAAI 2024. They fall into 4 topics.
See AAAI 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Human-AI and goal-conditioned · 65 papers
- End-to-End Autonomous Driving Through V2X Cooperation (42 citations)
- MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale (11 citations)
- Online Guidance Graph Optimization for Lifelong Multi-Agent Path Finding (11 citations)
- LNS2+RL: Combining Multi-agent Reinforcement Learning with Large Neighborhood Search in Multi-agent Path Finding (8 citations)
- Loosely Synchronized Rule-Based Planning for Multi-Agent Path Finding with Asynchronous Actions (7 citations)
- Multi-Modal Grounded Planning and Efficient Replanning for Learning Embodied Agents with a Few Examples (7 citations)
- MuMA-ToM: Multi-modal Multi-Agent Theory of Mind (7 citations)
- Orpheus: Engineering Multiagent Systems via Communicating Agents (7 citations)
- Walk Wisely on Graph: Knowledge Graph Reasoning with Dual Agents via Efficient Guidance-Exploration (6 citations)
- A Domain-Independent Agent Architecture for Adaptive Operation in Evolving Open Worlds (5 citations)
- CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuning (5 citations)
- MRBTP: Efficient Multi-Robot Behavior Tree Planning and Collaboration (5 citations)
and 53 more in the interactive map.
Games and equilibria · 38 papers
- A Unified Model of Direct and Indirect Reciprocity in Multichannel Games (2 citations)
- Balanced and Fair Partitioning of Friends (2 citations)
- EF2X Exists for Four Agents (2 citations)
- Every Bit Helps: Achieving the Optimal Distortion with a Few Queries (2 citations)
- Learning Nash Equilibrium of Markov Potential Games with a Shared Constraint via Primal-Dual Optimization (2 citations)
- Multi Agent Reinforcement Learning for Sequential Satellite Assignment Problems (2 citations)
- Operationalising Rawlsian Ethics for Fairness in Norm Learning Agents (2 citations)
- (Almost Full) EFX for Three (and More) Types of Agents (1 citation)
- Bounded Rationality Equilibrium Learning in Mean Field Games (1 citation)
- Decentralized Convergence to Equilibrium Prices in Trading Networks (1 citation)
- Deviate or Not: Learning Coalition Structures with Multiple-bit Observations in Games (1 citation)
- Explaining Decisions of Agents in Mixed-Motive Games (1 citation)
and 26 more in the interactive map.
Cooperative multi-agent RL · 21 papers
- Exploring the Efficacy of Multi-Agent Reinforcement Learning for Autonomous Cyber Defence: A CAGE Challenge 4 Perspective (15 citations)
- CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness (7 citations)
- Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems (5 citations)
- Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation (5 citations)
- Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization (5 citations)
- Scalable Decentralized Algorithms for Online Personalized Mean Estimation (5 citations)
- Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning (4 citations)
- Gradient-Guided Credit Assignment and Joint Optimization for Dependency-Aware Spatial Crowdsourcing (3 citations)
- GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Critic (3 citations)
- SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning (3 citations)
- AgentMixer: Multi-Agent Correlated Policy Factorization (1 citation)
- Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL (1 citation)
and 9 more in the interactive map.
LLM agents · 16 papers
- VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool (46 citations)
- BotSim: LLM-Powered Malicious Social Botnet Simulation (14 citations)
- SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration (14 citations)
- MDD-5k: A New Diagnostic Conversation Dataset for Mental Disorders Synthesized via Neuro-Symbolic LLM Agents (12 citations)
- WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration (12 citations)
- Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems (8 citations)
- Mitigating Social Bias in Large Language Models: A Multi-Objective Approach Within a Multi-Agent Framework (7 citations)
- Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models (5 citations)
- Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks (4 citations)
- LLM Agents Can Be Choice-Supportive Biased Evaluators: An Empirical Study (3 citations)
- Concept Matching with Agent for Out-of-Distribution Detection (2 citations)
- Mixture of Knowledge Minigraph Agents for Literature Review Generation (1 citation)
and 4 more in the interactive map.