Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning. However, standard frameworks like Group Relative Policy Optimization (GRPO) typically employ a uniform rollout budget, leading to resource inefficiency. Moreover, existing adaptive methods often rely on instance-level metrics, such as task pass rates, failing to capture the model's dynamic learning state. To address these limitations, we propose CoBA-RL, a reinforcement learning algorithm designed to adaptively allocate rollout budgets based on the model's evolving capability. Specifically, CoBA-RL utilizes a Capability-Oriented Value function to map tasks to their potential training gains and employs a heap-based greedy strategy to efficiently self-calibrate the distribution of computational resources to samples with high training value. Extensive experiments demonstrate that our approach effectively orchestrates the trade-off between exploration and exploitation, delivering consistent generalization improvements across multiple challenging benchmarks. These findings underscore that quantifying sample training value and optimizing budget allocation are pivotal for advancing LLM post-training efficiency.
SERA: Scale-Equalized Rollout Allocation for Maximum Likelihood Reinforcement Learning
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Nanyang Technological University（南洋理工大学）
UC Berkeley（加州大学伯克利分校）；University of Iowa（爱荷华大学）；Microsoft Research（微软研究院）
In crowd labeling, a large amount of unlabeled data instances are outsourced to a crowd of workers. Workers will be paid for each label they provide, but the labeling requester usually has only a limited amount of the budget. Since data instances have different levels of labeling difficulty and workers have different reliability, it is desirable to have an optimal policy to allocate the budget among all instance-worker pairs such that the overall labeling accuracy is maximized. We consider categorical labeling tasks and formulate the budget allocation problem as a Bayesian Markov decision proc…
Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs
National University of Singapore（新加坡国立大学）；Agency for Science, Technology, and Research (A*STAR)（新加坡科技研究局）；Singapore-MIT Alliance for Research and Technology Centre（新加坡-麻省理工研究与技术联盟中心）
HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Meituan（美团）；Institute for Advanced Algorithms Research（先进算法研究院）
Stochastic sequential decision making often requires hierarchical structure in the problem where each high-level action should be further planned with primitive states and actions. In addition, many real-world applications require a plan that satisfies constraints on the secondary costs such as risk measure or fuel consumption. In this paper, we propose a hierarchical constrained stochastic shortest path problem (HC-SSP) that meets those two crucial requirements in a single framework. Although HC-SSP provides a useful framework to model such planning requirements in many real-world application…
Sequential incentive marketing is an important approach for online businesses to acquire customers, increase loyalty and boost sales. How to effectively allocate the incentives so as to maximize the return (e.g., business objectives) under the budget constraint, however, is less studied in the literature. This problem is technically challenging due to the facts that 1) the allocation strategy has to be learned using historically logged data, which is counterfactual in nature, and 2) both the optimality and feasibility (i.e., that cost cannot exceed budget) needs to be assessed before being dep…
We study the sequential resource allocation problem where a decision maker repeatedly allocates budgets between resources. Motivating examples include allocating limited computing time or wireless spectrum bands to multiple users (i.e., resources). At each timestep, the decision maker should distribute its available budgets among different resources to maximize the expected reward, or equivalently to minimize the cumulative regret. In doing so, the decision maker should learn the value of the resources allocated for each user from feedback on each user's received reward. For example, users may…
CyberAgent, Inc.（CyberAgent公司）；The University of Tokyo（东京大学）；Columbia University（哥伦比亚大学）
We consider fixed-budget best-arm identification in two-armed Gaussian bandit problems. One of the longstanding open questions is the existence of an optimal strategy under which the probability of misidentification matches a lower bound. We show that a strategy following the Neyman allocation rule (Neyman, 1934) is asymptotically optimal when the gap between the expected rewards is small. First, we review a lower bound derived by Kaufmann et al. (2016). Then, we propose the "Neyman Allocation (NA)-Augmented Inverse Probability weighting (AIPW)" strategy, which consists of the sampling rule us…
Comparing Socially-Equitable Renewable Energy Budget Allocation MDP Policies in Mature and Emerging Economies
Management \& Technology University of Pennsylvania Philadelphia, PA, USA；Systems Engineering Institute Technology of Sepuluh Nopember (ITS) Surabaya, Indonesia；Systems Engineering King Fahd University of Petroleum
LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation
State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；School of Artificial Intelligence, Nanjing University（人工智能学院，南京大学）；Stepfun
ChampionKV: Head-Wise Adaptive Budget Allocation for KV Cache Compression
Sun Yat-sen University（中山大学）；The Chinese University of Hong Kong（香港中文大学）；University of Electronic Science and Technology of China（电子科技大学）；Tongji University（同济大学）；Hong Kong University（香港大学）
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology（国防科技大学并行与分布计算国家重点实验室，计算机科学与技术学院）
Budgeted pruning is the problem of pruning under resource constraints. In budgeted pruning, how to distribute the resources across layers (i.e., sparsity allocation) is the key problem. Traditional methods solve it by discretely searching for the layer-wise pruning ratios, which lacks efficiency. In this paper, we propose Differentiable Sparsity Allocation (DSA), an efficient end-to-end budgeted pruning flow. Utilizing a novel differentiable pruning process, DSA finds the layer-wise pruning ratios with gradient-based optimization. It allocates sparsity in continuous space, which is more effici…
The optimal allocation of resources for maximizing influence, spread of information or coverage, has gained attention in the past years, in particular in machine learning and data mining. But in applications, the parameters of the problem are rarely known exactly, and using wrong parameters can lead to undesirable outcomes. We hence revisit a continuous version of the Budget Allocation or Bipartite Influence Maximization problem introduced by Alon et al. (2012) from a robust optimization perspective, where an adversary may choose the least favorable parameters within a confidence set. The resu…
Due to concerns about human error in crowdsourcing, it is standard practice to collect labels for the same data point from multiple internet workers. We here show that the resulting budget can be used more effectively with a flexible worker assignment strategy that asks fewer workers to analyze easy-to-label data and more workers to analyze data that requires extra scrutiny. Our main contribution is to show how the allocations of the number of workers to a task can be computed optimally based on task features alone, without using worker profiles. Our target tasks are delineating cells in micro…
Spend Where It Counts: Dynamic Budget Allocation for Multi-Turn LLM Evaluation
Department of Computer Science（计算机科学系）；Technion, Israel（技术ion, 以色列）；Departments of Electrical and Computer Engineering and of Computer Science（电气与计算机工程系和计算机科学系）
Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning
The School of Computing and Information Systems, the University of Melbourne, Melbourne, Australia（墨尔本大学计算与信息系统学院）；Royal Melbourne Institute of Technology, Melbourne, Australia（皇家墨尔本理工学院）；Now at Google Australia（现就职于谷歌澳大利亚）
SKEMA Business School（SKEMA商学院）；Université Côte d’Azur（蔚蓝海岸大学）；UNSW Sydney（新南威尔士大学悉尼分校）
The optimal allocation of vaccines to population subgroups over time is a challenging health care management problem. In the context of a pandemic, the interaction between vaccination policies adopted by multiple agents and the cooperation (or lack thereof) creates a complex environment that affects the global transmission dynamics of the disease. In this study, we take the perspective of decision-making agents that aim to minimize the size of their susceptible populations and must allocate vaccine under limited supply. We assume that vaccine efficiency rates are unknown to agents and we propo…
BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东大数据分析与处理重点实验室）；Department of Computing, Faculty of Science and Engineering, Macquarie University（麦考瑞大学计算机系）；Machine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学机器学习系）
Series Expansion of Probability of Correct Selection for Improved Finite Budget Allocation in Ranking and Selection
PKU-Wuhan Institute for Artificial Intelligence（北大-武汉人工智能研究院）；Guanghua School of Management, Peking University（北京大学光华管理学院）；Xiangjiang Laboratory（湘江实验室）；Inria（法国国家信息与自动化研究所）；Univ Rennes（雷恩大学）；CNRS（法国国家科学研究中心）；IRISA（法国信息与随机系统研究所）
Online platforms often incentivize consumers to improve user engagement and platform revenue. Since different consumers might respond differently to incentives, individual-level budget allocation is an essential task in marketing campaigns. Recent advances in this field often address the budget allocation problem using a two-stage paradigm: the first stage estimates the individual-level treatment effects using causal inference algorithms, and the second stage invokes integer programming techniques to find the optimal budget allocation solution. Since the objectives of these two stages might no…
