Related papers: Post-Training and Test-Time Scaling of Generative …

Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end…

Maneuvering in dense traffic is a challenging task for autonomous vehicles because it requires reasoning about the stochastic behaviors of many other participants. In addition, the agent must achieve the maneuver within a limited time and…

Policy gradient reinforcement learning techniques enable an agent to directly learn an optimal action policy through the interactions with the environment. Nevertheless, despite its advantages, it sometimes suffers from slow convergence…

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches.…

Multi-agent systems perform well on general reasoning tasks. However, the lack of training in specialized areas hinders their accuracy. Current training methods train a unified large language model (LLM) for all agents in the system. This…

One of the key challenges to deep reinforcement learning (deep RL) is to ensure safety at both training and testing phases. In this work, we propose a novel technique of unsupervised action planning to improve the safety of on-policy…

Ensuring safety in autonomous driving (AD) remains a significant challenge, especially in highly dynamic and complex traffic environments where diverse agents interact and unexpected hazards frequently emerge. Traditional reinforcement…

Reinforcement learning (RL) is a promising avenue for post-training vision-language-action (VLA) models, but practical deployment is hindered by sparse rewards and unstable training. This work mitigates these challenges by introducing an…

Car-following models, as the essential part of traffic microscopic simulations, have been utilized to analyze and estimate longitudinal drivers' behavior since sixty years ago. The conventional car following models use mathematical formulas…

Recent studies have demonstrated the efficacy of integrating Group Relative Policy Optimization (GRPO) into flow matching models, particularly for text-to-image and text-to-video generation. However, we find that directly applying these…

Traffic simulation aims to learn a policy for traffic agents that, when unrolled in closed-loop, faithfully recovers the joint distribution of trajectories observed in the real world. Inspired by large language models, tokenized multi-agent…

Traffic simulation has gained a lot of interest for quantitative evaluation of self driving vehicles performance. In order for a simulator to be a valuable test bench, it is required that the driving policy animating each traffic agent in…

Large Language Models (LLMs) have demonstrated remarkable capabilities in knowledge acquisition, reasoning, and tool use, making them promising candidates for autonomous agent applications. However, training LLM agents for complex…

Neural Combinatorial Optimization (NCO) has emerged as a promising learning-based paradigm for addressing Vehicle Routing Problems (VRPs) by minimizing the need for extensive manual engineering. While existing NCO methods, trained on…

Multimodal Large Language Models (MLLMs) excel in vision-language reasoning but often struggle with structured perception tasks requiring precise localization and robustness. We propose a reinforcement learning framework that augments Group…

Offline reinforcement learning allows training reinforcement learning models on data from live deployments. However, it is limited to choosing the best combination of behaviors present in the training data. In contrast, simulation…

Many current behavior generation methods struggle to handle real-world traffic situations as they do not scale well with complexity. However, behaviors can be learned off-line using data-driven approaches. Especially, reinforcement learning…

Safe Reinforcement Learning (Safe RL) aims to train an RL agent to maximize its performance in real-world environments while adhering to safety constraints, as exceeding safety violation limits can result in severe consequences. In this…

Reinforcement Learning (RL) in partially observable environments poses significant challenges due to the complexity of learning under uncertainty. While additional information, such as that available in simulations, can enhance training,…

Unsupervised speech emotion recognition (SER) focuses on addressing the problem of data sparsity and annotation bias of emotional speech. Reinforcement learning (RL) is a promising method which enhances the performance through rule-based or…