Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these models suffer from overthinking, generating unnecessarily long and redundant reasoning even for simple questions, which substantially increases computational cost and response latency. While existing methods incorporate length rewards to GRPO to promote concise reasoning, they incur significant performance degradation. We identify the root cause: when rewards for correct but long rollouts are penalized, GRPO's group-relative advantage function can assign them negative advantages, actively discouraging valid reasoning. To overcome this, we propose Decoupled Reward Policy Optimization (DRPO), a novel framework that decouples the length-based learning signal of correct rollouts from incorrect ones. DRPO ensures that reward signals for correct rollouts are normalized solely within the positive group, shielding them from interference by negative samples. The DRPO's objective is grounded in integrating an optimized positive data distribution, which maximizes length-based rewards under a KL regularization, into a discriminative objective. We derive a closed-form solution for this distribution, enabling efficient computation of the objective and its gradients using only on-policy data and importance weighting. Of independent interest, this formulation is general and can incorporate other preference rewards of positive data beyond length. Experiments on mathematical reasoning tasks demonstrate DRPO's significant superiority over six efficient reasoning baselines. Notably, with a 1.5B model, our method achieves 77\% length reduction with only 1.1\% performance loss on simple questions like GSM8k dataset, while the follow-up baseline sacrifices 4.3\% for 68\% length reduction.

Large Language Models (LLMs) show strong reasoning abilities, often amplified by Chain-of-Thought (CoT) prompting and reinforcement learning (RL). Although RL algorithms can substantially improve reasoning, they struggle to expand reasoning boundaries because they learn from their own reasoning trajectories rather than acquiring external knowledge. Supervised fine-tuning (SFT) offers complementary benefits but typically requires large-scale data and risks overfit-ting. Recent attempts to combine SFT and RL face three main challenges: data inefficiency, algorithm-specific designs, and catastrophic forgetting. We propose a plug-and-play framework that dynamically integrates SFT into RL by selecting challenging examples for SFT. This approach reduces SFT data requirements and remains agnostic to the choice of RL or SFT algorithm. To mitigate catastrophic forgetting of RL-acquired skills during SFT, we select high-entropy tokens for loss calculation and freeze parameters identified as critical for RL. Our method achieves state-of-the-art (SoT A) reasoning performance using only 1.5% of the SFT data and 20.4% of the RL data used by prior SoT A, providing an efficient and plug-and-play solution for combining SFT and RL in reasoning post-training. Recent Large Language Models (LLMs) has shown reasoning capability (Jaech et al., 2024; Guo et al., 2025; Anthropic, 2025). The reasoning capability are highly dependent on the use of the Chain-of-Thought (CoT) thinking pattern trained by supervise fine-tuning (SFT) or reinforcement learning (RL). Although popular RL algorithms such as PPO (Schulman et al., 2017), GRPO (Guo et al., 2025), and DAPO (Y u et al., 2025) are promising in multiple reasoning tasks, recent studies argue that RL training does not truly extend a model's reasoning boundaries.

Performative reinforcement learning is an emerging dynamical decision making framework, which extends reinforcement learning to the common applications where the agent's policy can change the environmental dynamics. Existing works on performative reinforcement learning only aim at a performatively stable (PS) policy that maximizes an approximate value function. However, there is a provably positive constant gap between the PS policy and the desired performatively optimal (PO) policy that maximizes the original value function. In contrast, this work proposes a zeroth-order Frank-Wolfe algorithm (0-FW) algorithm with a zeroth-order approximation of the performative policy gradient in the Frank-Wolfe framework, and obtains \textbf{the first polynomial-time convergence to the desired PO} policy under the standard regularizer dominance condition. For the convergence analysis, we prove two important properties of the nonconvex value function. First, when the policy regularizer dominates the environmental shift, the value function satisfies a certain gradient dominance property, so that any stationary point (not PS) of the value function is a desired PO. Second, though the value function has unbounded gradient, we prove that all the sufficiently stationary points lie in a convex and compact policy subspace $Π_Δ$, where the policy value has a constant lower bound $Δ>0$ and thus the gradient becomes bounded and Lipschitz continuous. Experimental results also demonstrate that our 0-FW algorithm is more effective than the existing algorithms in finding the desired PO policy.

Effective cross-functional coordination is essential for enhancing firm-wide profitability, particularly in the face of growing organizational complexity and scale. Recent advances in artificial intelligence, especially in reinforcement learning (RL), offer promising avenues to address this fundamental challenge. This paper proposes a unified multi-agent RL framework tailored for joint optimization across distinct functional modules, exemplified via coordinating inventory replenishment and personalized product recommendation. We first develop an integrated theoretical model to capture the intricate interplay between these functions and derive analytical benchmarks that characterize optimal coordination. The analysis reveals synchronized adjustment patterns across products and over time, highlighting the importance of coordinated decision-making. Leveraging these insights, we design a novel multi-timescale multi-agent RL architecture that decomposes policy components according to departmental functions and assigns distinct learning speeds based on task complexity and responsiveness. Our model-free multi-agent design improves scalability and deployment flexibility, while multi-timescale updates enhance convergence stability and adaptability across heterogeneous decisions. We further establish the asymptotic convergence of the proposed algorithm. Extensive simulation experiments demonstrate that the proposed approach significantly improves profitability relative to siloed decision-making frameworks, while the behaviors of the trained RL agents align closely with the managerial insights from our theoretical model. Taken together, this work provides a scalable, interpretable RL-based solution to enable effective cross-functional coordination in complex business settings.

Shared micromobility systems, such as electric scooters and bikes, have gained widespread popularity as sustainable alternatives to traditional transportation modes. However, these systems face persistent challenges due to spatio-temporal demand fluctuations, often resulting in a mismatch between vehicle supply and user demand. Existing shared micromobility vehicle scheduling methods typically redistribute vehicles once or twice per day, which makes them vulnerable to performance degradation under atypical conditions. In this work, we design to augment existing micromobility scheduling methods by integrating a small number of autonomous shared micromobility vehicles (ASMVs), which possess self-rebalancing capabilities to dynamically adapt to real-time demand. Specifically, we introduce SMART, a hierarchical reinforcement learning framework that jointly optimizes high-level initial deployment and low-level real-time rebalancing for ASMVs. We evaluate our framework based on real-world e-scooter usage data from Chicago. Our experiment results show that our framework is highly effective and possesses strong generalization capability, allowing it to seamlessly integrate with existing vehicle scheduling methods and significantly enhance overall micromobility service performance.

Recent advances in large language models (LLMs) have sparked growing interest in building generalist agents that can learn through online interactions. However, applying reinforcement learning (RL) to train LLM agents in multi-turn, multi-task settings remains challenging due to lack of scalable infrastructure and stable training algorithms. In this work, we present the AgentRL framework for scalable multi-turn, multi-task agentic RL training. On the infrastructure side, AgentRL features a fully-asynchronous generation-training pipeline for efficient multi-turn RL. To support heterogeneous environment development in multi-task RL, we design a unified function-call based API interface, containerized environment development, and a centralized controller. On the algorithm side, we propose cross-policy sampling to encourage model exploration in multi-turn settings and task advantage normalization to stabilize multi-task training. Experiments show that AgentRL, trained on open LLMs across five agentic tasks, significantly outperforms GPT-5, Clause-Sonnet-4, DeepSeek-R1, and other open-source LLM agents. Multi-task training with AgentRL matches the best results among all task-specific models. AgentRL is open-sourced at https://github.com/THUDM/AgentRL. The algorithm and framework are adopted in building \textsc{\href{https://autoglm.zhipuai.cn}{AutoGLM}}.

Recent studies have increasingly focused on non-asymptotic convergence analyses for actor-critic (AC) algorithms. One such effort introduced a two-timescale critic-actor algorithm for the discounted cost setting using a tabular representation, where the usual roles of the actor and critic are reversed. However, only asymptotic convergence was established there. Subsequently, both asymptotic and non-asymptotic analyses of the critic-actor algorithm with linear function approximation were conducted. In our work, we introduce the first natural critic-actor algorithm with function approximation for the long-run average cost setting and under inequality constraints. We provide the non-asymptotic convergence guarantees for this algorithm. Our analysis establishes optimal learning rates and we also propose a modification to enhance sample complexity. We further show the results of experiments on three different Safety-Gym environments where our algorithm is found to be competitive in comparison with other well known algorithms.

Competitive search is a setting where document publishers modify them to improve their ranking in response to a query. Recently, publishers have increasingly leveraged LLMs to generate and modify competitive content. We introduce Reinforcement Learning from Ranker Feedback (RLRF), a framework that trains LLMs using preference datasets derived from ranking competitions. The goal of a publisher (LLM-based) agent is to optimize content for improved ranking while accounting for the strategies of competing agents. We generate the datasets using approaches that do not rely on human-authored data. We show that our proposed agents consistently and substantially outperform previously suggested approaches for LLM-based competitive document modification. We further show that our agents are effective with ranking functions they were not trained for (i.e., out of distribution) and they adapt to strategic opponents. These findings provide support to the significant potential of using reinforcement learning in competitive search.

Conditional Semantic Textual Similarity (C-STS) measures the semantic proximity between text segments under a specific condition, thereby overcoming the ambiguity inherent in traditional STS. However, existing methods are largely confined to discriminative models, failing to fully integrate recent breakthroughs in the NLP community concerning Large Language Models (LLMs) and Reinforcement Learning (RL). RL is a particularly well-suited paradigm for this task, as it can directly optimize the non-differentiable Spearman ranking metric and guide the reasoning process required by C-STS. However, we find that naively applying listwise RL fails to produce meaningful improvements, as the model is overwhelmed by complex, coarse-grained reward signals. To address this challenge, we introduce PoLi-RL, a novel Point-to-List Reinforcement Learning framework. PoLi-RL employs a two-stage curriculum: it first trains the model with simple pointwise rewards to establish fundamental scoring capabilities, then transitions to a hybrid reward that combines pointwise, pairwise, and listwise objectives to refine the model's ability to discern subtle semantic distinctions. Crucially, we propose an innovative Parallel Slice Ranking Reward (PSRR) mechanism that computes ranking rewards in parallel slices, where each slice comprises same-indexed completions from different samples. This provides a precise, differentiated learning signal for each individual completion, enabling granular credit assignment and effective optimization. On the official C-STS benchmark, PoLi-RL achieves a Spearman correlation coefficient of 48.18, establishing a new SOTA for the cross-encoder architecture. As the first work to successfully apply RL to C-STS, our study introduces a powerful and precise paradigm for training LLMs on complex, ranking-based conditional judgment tasks.

The growing reliance on large-scale data centers to run resource-intensive workloads has significantly increased the global carbon footprint, underscoring the need for sustainable computing solutions. While container orchestration platforms like Kubernetes help optimize workload scheduling to reduce carbon emissions, existing methods often depend on centralized machine learning models that raise privacy concerns and struggle to generalize across diverse environments. In this paper, we propose a federated learning approach for energy consumption prediction that preserves data privacy by keeping sensitive operational data within individual enterprises. By extending the Kubernetes Efficient Power Level Exporter (Kepler), our framework trains XGBoost models collaboratively across distributed clients using Flower's FedXgbBagging aggregation using a bagging strategy, eliminating the need for centralized data sharing. Experimental results on the SPECPower benchmark dataset show that our FL-based approach achieves 11.7 percent lower Mean Absolute Error compared to a centralized baseline. This work addresses the unresolved trade-off between data privacy and energy prediction efficiency in prior systems such as Kepler and CASPER and offers enterprises a viable pathway toward sustainable cloud computing without compromising operational privacy.