We have developed a high-performance Chinese Chess AI that operates without reliance on search algorithms. This AI has demonstrated the capability to compete at a level commensurate with the top 0.1\% of human players. By eliminating the search process typically associated with such systems, this AI achieves a Queries Per Second (QPS) rate that exceeds those of systems based on the Monte Carlo Tree Search (MCTS) algorithm by over a thousandfold and surpasses those based on the AlphaBeta pruning algorithm by more than a hundredfold. The AI training system consists of two parts: supervised learning and reinforcement learning. Supervised learning provides an initial human-like Chinese chess AI, while reinforcement learning, based on supervised learning, elevates the strength of the entire AI to a new level. Based on this training system, we carried out enough ablation experiments and discovered that 1. The same parameter amount of Transformer architecture has a higher performance than CNN on Chinese chess; 2. Possible moves of both sides as features can greatly improve the training process; 3. Selective opponent pool, compared to pure self-play training, results in a faster improvement curve and a higher strength limit. 4. Value Estimation with Cutoff(VECT) improves the original PPO algorithm training process and we will give the explanation.

Large language model (LLM)-based AI delegates are increasingly utilized to act on behalf of users, assisting them with a wide range of tasks through conversational interfaces. Despite their advantages, concerns arise regarding the potential risk of privacy leaks, particularly in scenarios involving social interactions. While existing research has focused on protecting privacy by limiting the access of AI delegates to sensitive user information, many social scenarios require disclosing private details to achieve desired outcomes, necessitating a balance between privacy protection and disclosure. To address this challenge, we conduct a pilot study to investigate user preferences for AI delegates across various social relations and task scenarios, and then propose a novel AI delegate system that enables privacy-conscious self-disclosure. Our user study demonstrates that the proposed AI delegate strategically protects privacy, pioneering its use in diverse and dynamic social interactions.

Standard multi-agent reinforcement learning (MARL) algorithms are vulnerable to sim-to-real gaps. To address this, distributionally robust Markov games (RMGs) have been proposed to enhance robustness in MARL by optimizing the worst-case performance when game dynamics shift within a prescribed uncertainty set. Solving RMGs remains under-explored, from problem formulation to the development of sample-efficient algorithms. A notorious yet open challenge is if RMGs can escape the curse of multiagency, where the sample complexity scales exponentially with the number of agents. In this work, we propose a natural class of RMGs where the uncertainty set of each agent is shaped by both the environment and other agents' strategies in a best-response manner. We first establish the well-posedness of these RMGs by proving the existence of game-theoretic solutions such as robust Nash equilibria and coarse correlated equilibria (CCE). Assuming access to a generative model, we then introduce a sample-efficient algorithm for learning the CCE whose sample complexity scales polynomially with all relevant parameters. To the best of our knowledge, this is the first algorithm to break the curse of multiagency for RMGs.

Robot soccer, in its full complexity, poses an unsolved research challenge. Current solutions heavily rely on engineered heuristic strategies, which lack robustness and adaptability. Deep reinforcement learning has gained significant traction in various complex robotics tasks such as locomotion, manipulation, and competitive games (e.g., AlphaZero, OpenAI Five), making it a promising solution to the robot soccer problem. This paper introduces MARLadona. A decentralized multi-agent reinforcement learning (MARL) training pipeline capable of producing agents with sophisticated team play behavior, bridging the shortcomings of heuristic methods. Further, we created an open-source multi-agent soccer environment based on Isaac Gym. Utilizing our MARL framework and a modified a global entity encoder as our core architecture, our approach achieves a 66.8% win rate against HELIOS agent, which employs a state-of-the-art heuristic strategy. Furthermore, we provided an in-depth analysis of the policy behavior and interpreted the agent's intention using the critic network.

How can individual agents coordinate their actions to achieve a shared objective in distributed systems? This challenge spans economic, technical, and sociological domains, each confronting scalability, heterogeneity, and conflicts between individual and collective goals. In economic markets, a common currency facilitates coordination, raising the question of whether such mechanisms can be applied in other contexts. This paper explores this idea within social media platforms, where social support (likes, shares, comments) acts as a currency that shapes content production and sharing. We investigate two key questions: (1) Can social support serve as an effective coordination tool, and (2) What role do influencers play in content creation and dissemination? Our formal analysis shows that social support can coordinate user actions similarly to money in economic markets. Influencers serve dual roles, aggregating content and acting as information proxies, guiding content producers in large markets. While imperfections in information lead to a "price of influence" and suboptimal outcomes, this price diminishes as markets grow, improving social welfare. These insights provide a framework for understanding coordination in distributed environments, with applications in both sociological systems and multi-agent AI systems.

Algorithmic fairness in recommender systems requires close attention to the needs of a diverse set of stakeholders that may have competing interests. Previous work in this area has often been limited by fixed, single-objective definitions of fairness, built into algorithms or optimization criteria that are applied to a single fairness dimension or, at most, applied identically across dimensions. These narrow conceptualizations limit the ability to adapt fairness-aware solutions to the wide range of stakeholder needs and fairness definitions that arise in practice. Our work approaches recommendation fairness from the standpoint of computational social choice, using a multi-agent framework. In this paper, we explore the properties of different social choice mechanisms and demonstrate the successful integration of multiple, heterogeneous fairness definitions across multiple data sets.

This paper concerns the consensus and formation of a network of mobile autonomous agents in adversarial settings where a group of malicious (compromised) agents are subject to deception attacks. In addition, the communication network is arbitrarily time-varying and subject to intermittent connections, possibly imposed by denial-of-service (DoS) attacks. We provide explicit bounds for network connectivity in an integral sense, enabling the characterization of the system's resilience to specific classes of adversarial attacks. We also show that under the condition of connectivity in an integral sense uniformly in time, the system is finite-gain $\mathcal{L}_{p}$ stable and uniformly exponentially fast consensus and formation are achievable, provided malicious agents are detected and isolated from the network. We present a distributed and reconfigurable framework with theoretical guarantees for detecting malicious agents, allowing for the resilient cooperation of the remaining cooperative agents. Simulation studies are provided to illustrate the theoretical findings.

Detecting cognitive biases in large language models (LLMs) is a fascinating task that aims to probe the existing cognitive biases within these models. Current methods for detecting cognitive biases in language models generally suffer from incomplete detection capabilities and a restricted range of detectable bias types. To address this issue, we introduced the 'MindScope' dataset, which distinctively integrates static and dynamic elements. The static component comprises 5,170 open-ended questions spanning 72 cognitive bias categories. The dynamic component leverages a rule-based, multi-agent communication framework to facilitate the generation of multi-round dialogues. This framework is flexible and readily adaptable for various psychological experiments involving LLMs. In addition, we introduce a multi-agent detection method applicable to a wide range of detection tasks, which integrates Retrieval-Augmented Generation (RAG), competitive debate, and a reinforcement learning-based decision module. Demonstrating substantial effectiveness, this method has shown to improve detection accuracy by as much as 35.10% compared to GPT-4. Codes and appendix are available at https://github.com/2279072142/MindScope.

Reinforcement learning with general utilities has recently gained attention thanks to its ability to unify several problems, including imitation learning, pure exploration, and safe RL. However, prior work for solving this general problem in a unified way has mainly focused on the tabular setting. This is restrictive when considering larger state-action spaces because of the need to estimate occupancy measures during policy optimization. In this work, we address this issue and propose to approximate occupancy measures within a function approximation class using maximum likelihood estimation (MLE). We propose a simple policy gradient algorithm (PG-OMA) where an actor updates the policy parameters to maximize the general utility objective whereas a critic approximates the occupancy measure using MLE. We provide a sample complexity analysis of PG-OMA showing that our occupancy measure estimation error only scales with the dimension of our function approximation class rather than the size of the state action space. Under suitable assumptions, we establish first order stationarity and global optimality performance bounds for the proposed PG-OMA algorithm for nonconcave and concave general utilities respectively. We complement our methodological and theoretical findings with promising empirical results showing the scalability potential of our approach compared to existing tabular count-based approaches.

This work extends the recent opinion dynamics model from Cheng et al., emphasizing the role of group pressure in consensus formation. We generalize the findings to incorporate social influence algorithms with general time-varying, opinion-dependent weights and multidimensional opinions, beyond bounded confidence dynamics. We demonstrate that, with uniformly positive conformity levels, group pressure consistently drives consensus and provide a tighter estimate for the convergence rate. Unlike previous models, the common public opinion in our framework can assume arbitrary forms within the convex hull of current opinions, offering flexibility applicable to real-world scenarios such as opinion polls with random participant selection. This analysis provides deeper insights into how group pressure mechanisms foster consensus under diverse conditions.