Yizhe Huang

Xinwei Song, Yizhe Huang, Dengji Zhao et al.

Reputation, the aggregation of peer assessments diffused through social networks, is a pivotal mechanism for promoting cooperation in social dilemmas ubiquitous to distributed multi-agent systems comprising agents with limited perception and cognitive capabilities. Exploring efficient reputation systems, comprising reputation assessment rules and reputation-based policies, is a long-standing challenge. Previous work assumes predefined reputation assessment rules or models reputation as an intrinsic reward to learn policies, compromising the methods' ability for generalization and adaptation. To address this, we propose a distributed multi-agent reinforcement learning method $\textbf{COOPER}$ ($\textbf{COOP}$eration with $\textbf{E}$mergent $\textbf{R}$eputation), which jointly learns reputation assessment rules and reputation-based policies entirely from environment rewards. Notably, leveraging the underlying mechanisms of reputation, we deliberately design the constituent modules of $\textbf{COOPER}$ and the data flows among them, overcoming the latency and noise in the feedback signal, caused by the deep entanglement between reputation and policy. Experiments on the donation game and the coin game in grid world environments demonstrate that $\textbf{COOPER}$ effectively adapts to various existing reputation systems and co-players. Furthermore, we observe the co-emergence of reputation norms and cooperation in self-play settings. These results hold robustly across diverse social network topologies, underscoring the generalizability and efficacy of our approach.

Yizhe Huang, Xingbo Wang, Hao Liu et al.

Traditional interactive environments limit agents' intelligence growth with fixed tasks. Recently, single-agent environments address this by generating new tasks based on agent actions, enhancing task diversity. We consider the decision-making problem in multi-agent settings, where tasks are further influenced by social connections, affecting rewards and information access. However, existing multi-agent environments lack a combination of adaptive physical surroundings and social connections, hindering the learning of intelligent behaviors. To address this, we introduce AdaSociety, a customizable multi-agent environment featuring expanding state and action spaces, alongside explicit and alterable social structures. As agents progress, the environment adaptively generates new tasks with social structures for agents to undertake. In AdaSociety, we develop three mini-games showcasing distinct social structures and tasks. Initial results demonstrate that specific social structures can promote both individual and collective benefits, though current reinforcement learning and LLM-based algorithms show limited effectiveness in leveraging social structures to enhance performance. Overall, AdaSociety serves as a valuable research platform for exploring intelligence in diverse physical and social settings. The code is available at https://github.com/bigai-ai/AdaSociety.

Haoxin Wang, Xianhan Peng, Xucheng Huang et al.

In this paper, we introduce ECom-Bench, the first benchmark framework for evaluating LLM agent with multimodal capabilities in the e-commerce customer support domain. ECom-Bench features dynamic user simulation based on persona information collected from real e-commerce customer interactions and a realistic task dataset derived from authentic e-commerce dialogues. These tasks, covering a wide range of business scenarios, are designed to reflect real-world complexities, making ECom-Bench highly challenging. For instance, even advanced models like GPT-4o achieve only a 10-20% pass^3 metric in our benchmark, highlighting the substantial difficulties posed by complex e-commerce scenarios. The code and data have been made publicly available at https://github.com/XiaoduoAILab/ECom-Bench to facilitate further research and development in this domain.

Rui Gao, Rohit Arora, Yizhe Huang

We study multistage distributionally robust linear optimization, where the uncertainty set is defined as a ball of distribution centered at a scenario tree using the nested distance. The resulting minimax problem is notoriously difficult to solve due to its inherent non-convexity. In this paper, we demonstrate that, under mild conditions, the robust risk evaluation of a given policy can be expressed in an equivalent recursive form. Furthermore, assuming stagewise independence, we derive equivalent dynamic programming reformulations to find an optimal robust policy that is time-consistent and well-defined on unseen sample paths. Our reformulations reconcile two modeling frameworks: the multistage-static formulation (with nested distance) and the multistage-dynamic formulation (with one-period Wasserstein distance). Moreover, we identify tractable cases when the value functions can be computed efficiently using convex optimization techniques.

Yizhe Huang, Bin Ling, Song-Chun Zhu et al.

Standard rational actor models often attribute cooperation failures in social dilemmas to insufficient incentives, overlooking the destabilizing effects of continuous utility maximization. To address this, we propose a framework of ``will" defined as a mechanism that persistently pursues goals while ignoring local cost-benefit fluctuations. We formalize the Willed Agents as potential minimizers, distinguishing them from cumulative utility maximization. Dynamical analysis of infinite population demonstrates that willed agents shrink the feasible state space, acting as boundary constraints that accelerate convergence in canonical social dilemmas. Through multi-agent simulations in a spatiotemporal Stag Hunt Game, we show that willed agents function as ``cooperation catalysts", enabling groups to surmount high-risk thresholds where purely utility maximization fails. We find that heterogeneous will strength promotes cooperation, and that agents who autonomously suspend rational re-evaluation can significantly outperform continuous optimizers. These findings suggest that successful cooperation relies on the cognitive capacity to strategically constrain calculation.

Yizhe Huang, Yang Liu, Ruiyu Zhao et al.

Large Language Model-based agents(LLM-based agents) are increasingly deployed in customer service, yet they often forget across sessions, repeat errors, and lack mechanisms for continual self-improvement. This makes them unreliable in dynamic settings where stability and consistency are critical. To better evaluate these properties, we emphasize two indicators: task success rate as a measure of overall effectiveness, and consistency metrics such as Pass$^k$ to capture reliability across multiple trials. To address the limitations of existing approaches, we propose MemOrb, a lightweight and plug-and-play verbal reinforcement memory layer that distills multi-turn interactions into compact strategy reflections. These reflections are stored in a shared memory bank and retrieved to guide decision-making, without requiring any fine-tuning. Experiments show that MemOrb significantly improves both success rate and stability, achieving up to a 63 percentage-point gain in multi-turn success rate and delivering more consistent performance across repeated trials. Our results demonstrate that structured reflection is a powerful mechanism for enhancing long-term reliability of frozen LLM agents in customer service scenarios.

Xiaoyuan Zhang, Yizhe Huang, Chengdong Ma et al.

Designing adaptive mechanisms to align individual and collective interests remains a central challenge in artificial social intelligence. Existing methods often struggle with modeling heterogeneous agents possessing persistent latent traits (e.g., skills, preferences) and dealing with complex multi-agent system dynamics. These challenges are compounded by the critical need for high sample efficiency due to costly real-world interactions. World Models, by learning to predict environmental dynamics, offer a promising pathway to enhance mechanism design in heterogeneous and complex systems. In this paper, we introduce a novel method named SWM-AP (Social World Model-Augmented Mechanism Design Policy Learning), which learns a social world model hierarchically modeling agents' behavior to enhance mechanism design. Specifically, the social world model infers agents' traits from their interaction trajectories and learns a trait-based model to predict agents' responses to the deployed mechanisms. The mechanism design policy collects extensive training trajectories by interacting with the social world model, while concurrently inferring agents' traits online during real-world interactions to further boost policy learning efficiency. Experiments in diverse settings (tax policy design, team coordination, and facility location) demonstrate that SWM-AP outperforms established model-based and model-free RL baselines in cumulative rewards and sample efficiency.

Yiwen Zhang, Ziang Chen, Fanqi Kong et al.

Large Language Models (LLMs) have been used to make decisions in complex scenarios, where they need models to think deeply, reason logically, and decide wisely. Many existing studies focus solely on multi-round conversations in social tasks or simulated environments, neglecting the various types of decisions and their interdependence. Current reinforcement learning methods struggle to consider the strategies of others during training. To address these issues, we first define a strategic decision-making problem that includes two types of decisions and their temporal dependencies. Furthermore, we propose **T**heory **o**f **M**ind **P**olicy **O**ptimization **(ToMPO)** algorithm to optimize the perception of other individual strategies and the game situation trends. Compared to the Group Relative Policy Optimization (GRPO) algorithm, ToMPO enhances the LLM's strategic decision-making mainly by: 1) generating rollouts based on reasoning the strategies of other individuals, 2) estimating advantages at both the graph-level and sample-level, and 3) balancing global and partial rewards. The ToMPO algorithm outperforms the GRPO method by 35% in terms of model output compliance and cooperative outcomes. Additionally, when compared to models with parameter sizes 100 times larger, it shows an 18% improvement. This demonstrates the effectiveness of the ToMPO algorithm in enhancing the model's strategic decision-making capabilities.

Yizhe Huang, Anji Liu, Fanqi Kong et al.

Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in mixed-motive environments remains a significant challenge. One feasible approach is to hierarchically model co-players' behavior based on inferring their characteristics. However, these methods often encounter difficulties in efficient reasoning and utilization of inferred information. To address these issues, we propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm that enables few-shot adaptation to unseen policies in mixed-motive environments. HOP is hierarchically composed of two modules: an opponent modeling module that infers others' goals and learns corresponding goal-conditioned policies, and a planning module that employs Monte Carlo Tree Search (MCTS) to identify the best response. Our approach improves efficiency by updating beliefs about others' goals both across and within episodes and by using information from the opponent modeling module to guide planning. Experimental results demonstrate that in mixed-motive environments, HOP exhibits superior few-shot adaptation capabilities when interacting with various unseen agents, and excels in self-play scenarios. Furthermore, the emergence of social intelligence during our experiments underscores the potential of our approach in complex multi-agent environments.