We study the problem of online multi-agent reinforcement learning (MARL) in environments with sparse rewards, where reward feedback is not provided at each interaction but only revealed at the end of a trajectory. This setting, though realistic, presents a fundamental challenge: the lack of intermediate rewards hinders standard MARL algorithms from effectively guiding policy learning. To address this issue, we propose a novel framework that integrates online inverse preference learning with multi-agent on-policy optimization into a unified architecture. At its core, our approach introduces an implicit multi-agent reward learning model, built upon a preference-based value-decomposition network, which produces both global and local reward signals. These signals are further used to construct dual advantage streams, enabling differentiated learning targets for the centralized critic and decentralized actors. In addition, we demonstrate how large language models (LLMs) can be leveraged to provide preference labels that enhance the quality of the learned reward model. Empirical evaluations on state-of-the-art benchmarks, including MAMuJoCo and SMACv2, show that our method achieves superior performance compared to existing baselines, highlighting its effectiveness in addressing sparse-reward challenges in online MARL.

Abstract--Efficient traffic signal control (TSC) is crucial for reducing congestion, travel delays, pollution, and for ensuring road safety. Traditional approaches, such as fixed signal control and actuated control, often struggle to handle dynamic traffic patterns. In this study, we propose a novel adaptive TSC framework that leverages Reinforcement Learning (RL), using the Proximal Policy Optimization (PPO) algorithm, to minimize total queue lengths across all signal phases. The challenge of efficiently representing highly stochastic traffic conditions for an RL controller is addressed through multiple state representations, including an expanded state space, an autoencoder representation, and a K-Planes-inspired representation. The proposed algorithm has been implemented using the Simulation of Urban Mobility (SUMO) traffic simulator and demonstrates superior performance over both traditional methods and other conventional RL-based approaches in reducing queue lengths. The best performing configuration achieves an approximately 29% reduction in average queue lengths compared to the traditional Webster method. Furthermore, comparative evaluation of alternative reward formulations demonstrates the effectiveness of the proposed queue-based approach, showcasing the potential for scalable and adaptive urban traffic management. I. INTRODUCTION Traffic signal control (TSC) is a crucial problem that needs to be addressed to manage traffic flows, ensure road safety, reduce delays, and increase efficiency and social benefits.

Lead optimization in drug discovery requires efficiently navigating vast chemical space through iterative cycles to enhance molecular properties while preserving structural similarity to the original lead compound. Despite recent advances, traditional optimization methods struggle with sample efficiency-achieving good optimization performance with limited oracle evaluations. Large Language Models (LLMs) provide a promising approach through their in-context learning and instruction following capabilities, which align naturally with these iterative processes. However, existing LLM-based methods fail to leverage this strength, treating each optimization step independently. To address this, we present POLO (Preference-guided multi-turn Optimization for Lead Optimization), which enables LLMs to learn from complete optimization trajectories rather than isolated steps. At its core, POLO introduces Preference-Guided Policy Optimization (PGPO), a novel reinforcement learning algorithm that extracts learning signals at two complementary levels: trajectory-level optimization reinforces successful strategies, while turn-level preference learning provides dense comparative feedback by ranking intermediate molecules within each trajectory. Through this dual-level learning from intermediate evaluation, POLO achieves superior sample efficiency by fully exploiting each costly oracle call. Extensive experiments demonstrate that POLO achieves 84% average success rate on single-property tasks (2.3x better than baselines) and 50% on multi-property tasks using only 500 oracle evaluations, significantly advancing the state-of-the-art in sample-efficient molecular optimization.

Abstract-- Autonomous docking between Unmanned Aerial V ehicles (UA Vs) and ground robots is essential for heterogeneous systems, yet most existing approaches target wheeled platforms whose limited mobility constrains exploration in complex terrains. Quadruped robots offer superior adaptability but undergo frequent posture variations, making it difficult to provide a stable landing surface for UA Vs. T o address these challenges, we propose an autonomous UA V-quadruped docking framework for GPS-denied environments. On the quadruped side, a Hybrid Internal Model with Horizontal Alignment (HIM-HA), learned via deep reinforcement learning, actively stabilizes the torso to provide a level platform. On the UA V side, a three-phase strategy is adopted, consisting of long-range acquisition with a median-filtered YOLOv8 detector, close-range tracking with a constraint-aware controller that integrates a Nonsingular Fast T erminal Sliding Mode Controller (NFTSMC) and a logarithmic Barrier Function (BF) to guarantee finite-time error convergence under field-of-view (FOV) constraints, and terminal descent guided by a Safety Period (SP) mechanism that jointly verifies tracking accuracy and platform stability. I. INTRODUCTION Heterogeneous cooperative systems that integrate Unmanned Aerial V ehicles (UA Vs) and Unmanned Ground V ehicles (UGVs) can expand operational scope and improve efficiency compared to single-domain platforms [1]. Autonomous docking is a key capability for many UA V-UGV collaborative tasks, yet most existing schemes focus on wheeled UGVs, whose mobility is restricted to flat terrain, limiting exploration in complex environments. Moreover, dynamic docking requires UA Vs to achieve precise localization and safe landing on moving platforms, imposing high demands on sensor fusion and robust control [2]. Quadruped robots, with their legged morphology, surpass wheeled and tracked UGVs in unstructured terrains and enable UA V collaboration in challenging environments such as mountains or tunnels.

Developing custom reasoning models via Reinforcement Learning (RL) that can incorporate organization-specific knowledge has great potential to address problems faced by enterprise customers. In many of these problems, the reward function is verifiable, a setting termed RL with Verifiable Rewards (RLVR). We apply RLVR to a popular data science benchmark called BIRD that measures the ability of an AI agent to convert a natural language query for a database to SQL executions. We apply a simple and general-purpose training recipe involving careful prompt and model selection, a warm-up stage using our offline RL approach called TAO, followed by rigorous online RLVR training. With no additional training data beyond the BIRD training set and no use of proprietary models, our very first submission to the BIRD leaderboard reached state-of-the-art accuracy on the private test set: 73.56% without self-consistency and 75.68% with self-consistency. In the latter case, our model also required fewer generations than the second-best approach. While BIRD is only a proxy task, the simplicity of our framework makes it broadly applicable to enterprise domains such as business intelligence, data science, and coding.