Recent advancements in Large Language Models(LLMs) have demonstrated their capabilities not only in reasoning but also in invoking external tools, particularly search engines. However, teaching models to discern when to invoke search and when to rely on their internal knowledge remains a significant challenge. Existing reinforcement learning approaches often lead to redundant search behaviors, resulting in inefficiencies and over-cost. In this paper, we propose SEM, a novel post-training reinforcement learning framework that explicitly trains LLMs to optimize search usage. By constructing a balanced dataset combining MuSiQue and MMLU, we create scenarios where the model must learn to distinguish between questions it can answer directly and those requiring external retrieval. We design a structured reasoning template and employ Group Relative Policy Optimization(GRPO) to post-train the model's search behaviors. Our reward function encourages accurate answering without unnecessary search while promoting effective retrieval when needed. Experimental results demonstrate that our method significantly reduces redundant search operations while maintaining or improving answer accuracy across multiple challenging benchmarks. This framework advances the model's reasoning efficiency and extends its capability to judiciously leverage external knowledge.

The vision of sixth-generation (6G) wireless networks paves the way for the seamless integration of digital twins into vehicular networks, giving rise to a Vehicular Digital Twin Network (VDTN). The large amount of computing resources as well as the massive amount of spatial-temporal data in Digital Twin (DT) domain can be utilized to enhance the communication and control performance of Internet of Vehicle (IoV) systems. In this article, we first propose the architecture of VDTN, emphasizing key modules that center on functions related to the joint optimization of control and communication. We then delve into the intricacies of the multitimescale decision process inherent in joint optimization in VDTN, specifically investigating the dynamic interplay between control and communication. To facilitate the joint optimization, we define two Value of Information (VoI) concepts rooted in control performance. Subsequently, utilizing VoI as a bridge between control and communication, we introduce a novel joint optimization framework, which involves iterative processing of two Deep Reinforcement Learning (DRL) modules corresponding to control and communication to derive the optimal policy. Finally, we conduct simulations of the proposed framework applied to a platoon scenario to demonstrate its effectiveness in ensu

As Radio Access Networks (RAN) evolve toward AI-native architectures, intelligent modules such as xApps and rApps are expected to make increasingly autonomous decisions across scheduling, mobility, and resource management domains. However, these agents remain fundamentally stateless, treating each decision as isolated, lacking any persistent memory of prior events or outcomes. This reactive behavior constrains optimization, especially in environments where network dynamics exhibit episodic or recurring patterns. In this work, we propose RAN Cortex, a memory-augmented architecture that enables contextual recall in AI-based RAN decision systems. RAN Cortex introduces a modular layer composed of four elements: a context encoder that transforms network state into high-dimensional embeddings, a vector-based memory store of past network episodes, a recall engine to retrieve semantically similar situations, and a policy interface that supplies historical context to AI agents in real time or near-real time. We formalize the retrieval-augmented decision problem in the RAN, present a system architecture compatible with O-RAN interfaces, and analyze feasible deployments within the Non-RT and Near-RT RIC domains. Through illustrative use cases such as stadium traffic mitigation and mobility management in drone corridors, we demonstrate how contextual memory improves adaptability, continuity, and overall RAN intelligence. This work introduces memory as a missing primitive in AI-native RAN designs and provides a framework to enable "learning agents" without the need for retraining or centralized inference

Reinforcement learning (RL)-based heating, ventilation, and air conditioning (HVAC) control has emerged as a promising technology for reducing building energy consumption while maintaining indoor thermal comfort. However, the efficacy of such strategies is influenced by the background climate and their implementation may potentially alter both the indoor climate and local urban climate. This study proposes an integrated framework combining RL with an urban climate model that incorporates a building energy model, aiming to evaluate the efficacy of RL-based HVAC control across different background climates, impacts of RL strategies on indoor climate and local urban climate, and the transferability of RL strategies across cities. Our findings reveal that the reward (defined as a weighted combination of energy consumption and thermal comfort) and the impacts of RL strategies on indoor climate and local urban climate exhibit marked variability across cities with different background climates. The sensitivity of reward weights and the transferability of RL strategies are also strongly influenced by the background climate. Cities in hot climates tend to achieve higher rewards across most reward weight configurations that balance energy consumption and thermal comfort, and those cities with more varying atmospheric temperatures demonstrate greater RL strategy transferability. These findings underscore the importance of thoroughly evaluating RL-based HVAC control strategies in diverse climatic contexts. This study also provides a new insight that city-to-city learning will potentially aid the deployment of RL-based HVAC control.

To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human preferences and optimizing policies via reinforcement learning algorithms. However, existing RLHF methods often misinterpret trajectories as being generated by an optimal policy, causing inaccurate likelihood estimation and suboptimal learning. Inspired by Direct Preference Optimization framework which directly learns optimal policy without explicit reward, we propose policy-labeled preference learning (PPL), to resolve likelihood mismatch issues by modeling human preferences with regret, which reflects behavior policy information. We also provide a contrastive KL regularization, derived from regret-based principles, to enhance RLHF in sequential decision making. Experiments in high-dimensional continuous control tasks demonstrate PPL's significant improvements in offline RLHF performance and its effectiveness in online settings.

Synthesizability in small molecule generative design remains a bottleneck. Existing works that do consider synthesizability can output predicted synthesis routes for generated molecules. However, there has been minimal attention in addressing the ease of synthesis and enabling flexibility to incorporate desired reaction constraints. In this work, we propose a small molecule generative design framework that enables steerable and granular synthesizability control. Generated molecules satisfy arbitrary multi-parameter optimization objectives with predicted synthesis routes containing pre-defined allowed reactions, while optionally avoiding others. One can also enforce that all reactions belong to a pre-defined set. We show the capability to mix-and-match these reaction constraints across the most common medicinal chemistry transformations. Next, we show how our framework can be used to valorize industrial byproducts towards de novo optimized molecules. Going further, we demonstrate how granular control over synthesizability constraints can loosely mimic virtual screening of ultra-large make-on-demand libraries. Using only a single GPU, we generate and dock 15k molecules to identify promising candidates in Freedom 4.0 constituting 142B make-on-demand molecules (assessing only 0.00001% of the library). Generated molecules satisfying the reaction constraints have > 90% exact match rate. Lastly, we benchmark our framework against recent synthesizability-constrained generative models and demonstrate the highest sample efficiency even when imposing the additional constraint that all molecules must be synthesizable from a single reaction type. The main theme is demonstrating that a pre-trained generalist molecular generative model can be incentivized to generate property-optimized small molecules under challenging synthesizability constraints through reinforcement learning.

Federated Learning (FL) enables distributed machine learning training while preserving privacy, representing a paradigm shift for data-sensitive and decentralized environments. Despite its rapid advancements, FL remains a complex and multifaceted field, requiring a structured understanding of its methodologies, challenges, and applications. In this survey, we introduce a meta-framework perspective, conceptualising FL as a composition of modular components that systematically address core aspects such as communication, optimisation, security, and privacy. We provide a historical contextualisation of FL, tracing its evolution from distributed optimisation to modern distributed learning paradigms. Additionally, we propose a novel taxonomy distinguishing Aggregation from Alignment, introducing the concept of alignment as a fundamental operator alongside aggregation. To bridge theory with practice, we explore available FL frameworks in Python, facilitating real-world implementation. Finally, we systematise key challenges across FL sub-fields, providing insights into open research questions throughout the meta-framework modules. By structuring FL within a meta-framework of modular components and emphasising the dual role of Aggregation and Alignment, this survey provides a holistic and adaptable foundation for understanding and advancing FL research and deployment.

Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL). Without clear feedback on actions at each step in sparse-reward setting, previous methods struggle with precise credit assignment among agents and effective exploration. In this paper, we introduce a novel method to deal with both credit assignment and exploration problems in reward-sparse domains. Accordingly, we propose an algorithm that calculates the Influence Scope of Agents (ISA) on states by taking specific value of the dimensions/attributes of states that can be influenced by individual agents. The mutual dependence between agents' actions and state attributes are then used to calculate the credit assignment and to delimit the exploration space for each individual agent. We then evaluate ISA in a variety of sparse-reward multi-agent scenarios. The results show that our method significantly outperforms the state-of-art baselines.

In various scientific and engineering domains, where data acquisition is costly, such as in medical imaging, environmental monitoring, or remote sensing, strategic sampling from unobserved regions, guided by prior observations, is essential to maximize target discovery within a limited sampling budget. In this work, we introduce Diffusion-guided Active Target Discovery (DiffATD), a novel method that leverages diffusion dynamics for active target discovery. DiffATD maintains a belief distribution over each unobserved state in the environment, using this distribution to dynamically balance exploration-exploitation. Exploration reduces uncertainty by sampling regions with the highest expected entropy, while exploitation targets areas with the highest likelihood of discovering the target, indicated by the belief distribution and an incrementally trained reward model designed to learn the characteristics of the target. DiffATD enables efficient target discovery in a partially observable environment within a fixed sampling budget, all without relying on any prior supervised training. Furthermore, DiffATD offers interpretability, unlike existing black-box policies that require extensive supervised training. Through extensive experiments and ablation studies across diverse domains, including medical imaging and remote sensing, we show that DiffATD performs significantly better than baselines and competitively with supervised methods that operate under full environmental observability.

Game-theoretic resource allocation on graphs (GRAG) involves two players competing over multiple steps to control nodes of interest on a graph, a problem modeled as a multi-step Colonel Blotto Game (MCBG). Finding optimal strategies is challenging due to the dynamic action space and structural constraints imposed by the graph. To address this, we formulate the MCBG as a Markov Decision Process (MDP) and apply Reinforcement Learning (RL) methods, specifically Deep Q-Network (DQN) and Proximal Policy Optimization (PPO). To enforce graph constraints, we introduce an action-displacement adjacency matrix that dynamically generates valid action sets at each step. We evaluate RL performance across a variety of graph structures and initial resource distributions, comparing against random, greedy, and learned RL policies. Experimental results show that both DQN and PPO consistently outperform baseline strategies and converge to a balanced $50\%$ win rate when competing against the learned RL policy. Particularly, on asymmetric graphs, RL agents successfully exploit structural advantages and adapt their allocation strategies, even under disadvantageous initial resource distributions.