English
Related papers

Related papers: Programming by Rewards

200 papers

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

Machine Learning · Computer Science 2025-08-01 Tao He , Rongchuan Mu , Lizi Liao , Yixin Cao , Ming Liu , Bing Qin

Conventional reward modeling relies on gradient descent over neural weights, creating opaque, data-hungry "black boxes." We propose a paradigm shift from implicit to explicit reward parameterization, recasting optimization from continuous…

Machine Learning · Computer Science 2026-02-06 Lipeng Xie , Sen Huang , Zhuo Zhang , Anni Zou , Yunpeng Zhai , Dingchao Ren , Kezun Zhang , Haoyuan Hu , Boyin Liu , Haoran Chen , Zhaoyang Liu , Bolin Ding

Reward models (RMs), which are central to existing post-training methods, aim to align LLM outputs with human values by providing feedback signals during fine-tuning. However, existing RMs struggle to capture nuanced, user-specific…

Machine Learning · Computer Science 2025-08-21 Mengdi Li , Guanqiao Chen , Xufeng Zhao , Haochen Wen , Shu Yang , Di Wang

Large Language Models (LLMs) are prone to hallucination, especially during multi-hop and reasoning-intensive tasks such as mathematical problem solving. While Outcome Reward Models verify only final answers, Process Reward Models (PRMs)…

Computation and Language · Computer Science 2025-05-27 Tej Deep Pala , Panshul Sharma , Amir Zadeh , Chuan Li , Soujanya Poria

Existing approaches to synthesize reactive systems from declarative specifications mostly rely on Binary Decision Diagrams (BDDs), inheriting their scalability issues. We present novel algorithms for safety specifications that use decision…

Logic in Computer Science · Computer Science 2016-04-22 Roderick Bloem , Uwe Egly , Patrick Klampfl , Robert Könighofer , Florian Lonsing , Martina Seidl

Pragmatic reasoning helps interlocutors infer intended meaning from ambiguous or underspecified messages by considering shared context and counterfactual alternatives. Similar challenges arise in natural language-to-code generation, where…

Computation and Language · Computer Science 2026-05-26 Zhuchen Cao , Sven Apel , Adish Singla , Vera Demberg

We present a new method for design problems wherein the goal is to maximize or specify the value of one or more properties of interest. For example, in protein design, one may wish to find the protein sequence that maximizes fluorescence.…

Machine Learning · Computer Science 2021-05-13 David H. Brookes , Hahnbeom Park , Jennifer Listgarten

Empirical software engineering is concerned with the design and analysis of empirical studies that include software products, processes, and resources. Optimization is a form of data analytics in support of human decision-making.…

Software Engineering · Computer Science 2019-12-05 Guenther Ruhe

The usage of Rational Speech Acts (RSA) framework has been successful in building \emph{pragmatic} program synthesizers that return programs which, in addition to being logically consistent with user-generated examples, account for the fact…

Programming Languages · Computer Science 2024-07-17 Yewen Pu , Saujas Vaduguru , Priyan Vaithilingam , Elena Glassman , Daniel Fried

To convey desired behavior to a Reinforcement Learning (RL) agent, a designer must choose a reward function for the environment, arguably the most important knob designers have in interacting with RL agents. Although many reward functions…

Machine Learning · Computer Science 2022-06-01 Henry Sowerby , Zhiyuan Zhou , Michael L. Littman

RL with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving the reasoning abilities of large language models (LLMs). Current methods rely primarily on policy optimization frameworks like PPO and GRPO, which follow…

Machine Learning · Computer Science 2025-09-30 Haoran He , Yuxiao Ye , Qingpeng Cai , Chen Hu , Binxing Jiao , Daxin Jiang , Ling Pan

While direct policy optimization methods exist, pioneering LLMs are fine-tuned with reinforcement learning from human feedback (RLHF) to generate better responses under the supervision of a reward model learned from preference data. One…

Machine Learning · Computer Science 2025-06-10 Chuheng Zhang , Wei Shen , Li Zhao , Xuyun Zhang , Xiaolong Xu , Wanchun Dou , Jiang Bian

In this paper, we propose a novel incentive based Demand Response (DR) program with a self reported baseline mechanism. The System Operator (SO) managing the DR program recruits consumers or aggregators of DR resources. The recruited…

Systems and Control · Electrical Eng. & Systems 2024-12-20 Deepan Muthirayan , Enrique Baeyens , Pratyush Chakraborty , Kameshwar Poolla , Pramod P. Khargonekar

Document summarisation can be formulated as a sequential decision-making problem, which can be solved by Reinforcement Learning (RL) algorithms. The predominant RL paradigm for summarisation learns a cross-input policy, which requires…

Computation and Language · Computer Science 2019-07-31 Yang Gao , Christian M. Meyer , Mohsen Mesgar , Iryna Gurevych

We introduce a novel class of algorithms to efficiently approximate the unknown return distributions in policy evaluation problems from distributional reinforcement learning (DRL). The proposed distributional dynamic programming algorithms…

Machine Learning · Statistics 2024-07-22 Julian Gerstenberg , Ralph Neininger , Denis Spiegel

Process reward models (PRMs) have shown success in complex reasoning tasks for large language models (LLMs). However, their application to machine translation (MT) remains underexplored due to the lack of systematic methodologies and…

Computation and Language · Computer Science 2025-09-22 Zhaopeng Feng , Jiahan Ren , Jiayuan Su , Jiamei Zheng , Hongwei Wang , Zuozhu Liu

Many popular piecewise regression models rely on minimizing a cost function on the model fit with a linear penalty on the number of segments. However, this penalty does not take into account varying complexities of the model functions on…

Methodology · Statistics 2025-03-06 Stefan Volz , Martin Storath , Andreas Weinmann

We present the first model-free Reinforcement Learning (RL) algorithm to synthesise policies for an unknown Markov Decision Process (MDP), such that a linear time property is satisfied. The given temporal property is converted into a Limit…

Machine Learning · Computer Science 2019-02-19 Mohammadhosein Hasanbeig , Alessandro Abate , Daniel Kroening

Recent advancements in improving the reasoning capabilities of Large Language Models have underscored the efficacy of Process Reward Models (PRMs) in addressing intermediate errors through structured feedback mechanisms. This study analyzes…

Computation and Language · Computer Science 2025-06-03 Zhengyu Chen , Yudong Wang , Teng Xiao , Ruochen Zhou , Xuesheng Yang , Wei Wang , Zhifang Sui , Jingang Wang

Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-data performance of the full tune-then-deploy procedure. We…

Machine Learning · Statistics 2026-05-08 Yang Xu , Jiefu Zhang , Haixiang Sun , Zihan Zhou , Tianyu Cao , Vaneet Aggarwal