Author name cluster

Jiaxun Cui

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

AAMAS Conference 2026 Conference Paper

CoopReflect: Towards Natural Language Communication for Cooperative Autonomous Driving via Multi-Agent Learning

Jiaxun Cui
Chen Tang
Jarrett Holtz
Janice Nguyen
Alessandro G. Allievi
Hang Qiu
Peter Stone

Past work has demonstrated that autonomous vehicles can drive more safely if they communicate with each other. However, this communication is usually not human-understandable. Using natural language as a vehicle-to-vehicle (V2V) communication protocol offers the potential for autonomous vehicles to drive cooperatively not only with each other but also with human drivers. To explore the potential use of natural language for V2V communication, we develop LLM-based driving agents and study their interactions in a new simulation environment, TalkingVehiclesGym, which features traffic scenarios where communication can potentially help avoid imminent collisions and/or support efficient traffic flow. While LLM agents relying solely on chain-of-thought reasoning struggle to coordinate effectively, we introduce CoopReflect, a multi-agent learningframeworkthatequipsagentswithknowledgeforbothnatural language message generation and high-level decision-making through trial and error and multi-agent debriefing. Experiments show that CoopReflect produces more meaningful and humanunderstandable messages than existing baselines, enabling stronger cooperation. Finally, we distill scenario-specific knowledge into a unified language model policy, achieving cross-scenario generalization and substantially reducing decision-making latency. Our code and demo videos are available at https: //talking-vehicles. github. io/

PDF

AAMAS Conference 2026 Conference Paper

VGC-Bench: Towards Mastering Diverse Team Strategies in Competitive Pokémon

Cameron L. Angliss
Jiaxun Cui
Jiaheng Hu
Arrasy Rahman
Peter Stone

Developing AI agents that can robustly adapt to varying strategic landscapes without retraining is a central challenge in multi-agent learning. Pokémon Video Game Championships (VGC) is a domain with a vast space of approximately 10139 team configurations. The combinatorial nature of team building in Pokémon VGC causes optimal strategies to vary substantially depending on both the controlled team and the opponent’s team, making generalization uniquely challenging. To advance research on this problem, we introduce VGC-Bench: a benchmark that provides critical infrastructure, standardizes evaluation protocols, and supplies a human-play dataset of over 700, 000 battle logs and a range of baseline agents based on heuristics, large language models, behavior cloning, and multi-agent reinforcement learning with empirical game-theoretic methods such as self-play, fictitious play, and double oracle. In the restricted setting where an agent is trained and evaluated in a mirror match with a single team configuration, our methods can win against a professional VGC competitor. We repeat this training and evaluation with progressively larger team sets and find that as the number of teams increases, the best-performing algorithm in the single-team setting has worse performance and is more exploitable, but has improved generalization to unseen teams. Our code, dataset, and baseline models are open-sourced at https: //github. com/cameronangliss/vgc-bench.

PDF

NeurIPS Conference 2025 Conference Paper

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Chandler Smith
Marwa Abdulhai
Manfred Díaz
Marko Tesic
Rakshit Trivedi
Sasha Vezhnevets
Lewis Hammond
Jesse Clifton

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

PDF Details

AAMAS Conference 2024 Conference Paper

Communication and Generalization in Multi-Agent Learning

Jiaxun Cui

Significant challenges exist in robustly interacting and communicating with a diverse array of agents, especially in intricate settings like autonomous driving where AI agents and humans coexist. This work approaches these challenges from three perspectives: generalization of agent policies, development of communicationsupporting representations, and interactions between humans and AI agents using natural language. We provide an overview of preliminary achievements in each area and outline proposed research focusing on enhancing cooperative driving through natural language communication, aiming to comprehensively address these complex multi-agent interaction challenges.

PDF

AAAI Conference 2024 Conference Paper

Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agents

Muhammad Rahman
Jiaxun Cui
Peter Stone

Robustly cooperating with unseen agents and human partners presents significant challenges due to the diverse cooperative conventions these partners may adopt. Existing Ad Hoc Teamwork (AHT) methods address this challenge by training an agent with a population of diverse teammate policies obtained through maximizing specific diversity metrics. However, prior heuristic-based diversity metrics do not always maximize the agent's robustness in all cooperative problems. In this work, we first propose that maximizing an AHT agent's robustness requires it to emulate policies in the minimum coverage set (MCS), the set of best-response policies to any partner policies in the environment. We then introduce the L-BRDiv algorithm that generates a set of teammate policies that, when used for AHT training, encourage agents to emulate policies from the MCS. L-BRDiv works by solving a constrained optimization problem to jointly train teammate policies for AHT training and approximating AHT agent policies that are members of the MCS. We empirically demonstrate that L-BRDiv produces more robust AHT agents than state-of-the-art methods in a broader range of two-player cooperative problems without the need for extensive hyperparameter tuning for its objectives. Our study shows that L-BRDiv outperforms the baseline methods by prioritizing discovering distinct members of the MCS instead of repeatedly finding redundant policies.

PDF Details DOI

ICLR Conference 2023 Conference Paper

MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection

Jiaxun Cui
Xiaomeng Yang
Mulong Luo
Geunbae Lee
Peter Stone 0001
Hsien-Hsin S. Lee
Benjamin Lee
G. Edward Suh

Security vulnerabilities in computer systems raise serious concerns as computers process an unprecedented amount of private and sensitive data today. Cache timing attacks (CTA) pose an important practical threat as they can effectively breach many protection mechanisms in today’s systems. However, the current detection techniques for cache timing attacks heavily rely on heuristics and expert knowledge, which can lead to brittleness and the inability to adapt to new attacks. To mitigate the CTA threat, we propose MACTA, a multi-agent reinforcement learning (MARL) approach that leverages population-based training to train both attackers and detectors. Following best practices, we develop a realistic simulated MARL environment, MA-AUTOCAT, which enables training and evaluation of cache-timing attackers and detectors. Our empirical results suggest that MACTA is an effective solution without any manual input from security experts. MACTA detectors can generalize to a heuristic attack not exposed in training with a 97.8% detection rate and reduce the attack bandwidth of adaptive attackers by 20% on average. In the meantime, MACTA attackers are qualitatively more effective than other attacks studied, and the average evasion rate of MACTA attackers against an unseen state-of-the-art detector can reach up to 99%. Furthermore, we found that agents equipped with a Transformer encoder can learn effective policies in situations when agents with multi-layer perceptron encoders do not in this environment, suggesting the potential of Transformer structures in CTA problems.

Details

AAMAS Conference 2021 Conference Paper

Scalable Multiagent Driving Policies for Reducing Traffic Congestion

Jiaxun Cui
William Macke
Harel Yedidsion
Aastha Goyal
Daniel Urieli
Peter Stone

Traffic congestion is a major challenge in modern urban settings. The industry-wide development of autonomous and automated vehicles (AVs) motivates the question of how can AVs contribute to congestion reduction. Past research has shown that in small scale mixed traffic scenarios with both AVs and human-driven vehicles, a small fraction of AVs executing a controlled multiagent driving policy can mitigate congestion. In this paper, we scale up existing approaches and develop new multiagent driving policies for AVs in scenarios with greater complexity. We start by showing that a congestion metric used by past research is manipulable in open road network scenarios where vehicles dynamically join and leave the road. We then propose using a different metric that is robust to manipulation and reflects open network traffic efficiency. Next, we propose a modular transfer reinforcement learning approach, and use it to scale up a multiagent driving policy to outperform human-like traffic and existing approaches in a simulated realistic scenario, which is an order of magnitude larger than past scenarios (hundreds instead of tens of vehicles). Additionally, our modular transfer learning approach saves up to 80% of the training time in our experiments, by focusing its data collection on key locations in the network. Finally, we show for the first time a distributed multiagent policy that improves congestion over human-driven traffic. The distributed approach is more realistic and practical, as it relies solely on existing sensing and actuation capabilities, and does not require adding new communication infrastructure.

PDF