English
Related papers

Related papers: Adaptive Generate-Rank-Verify: Inference-Time Sear…

200 papers

Active Learning (AL) is a user-interactive approach aimed at reducing annotation costs by selecting the most crucial examples to label. Although AL has been extensively studied for image classification tasks, the specific scenario of…

Computer Vision and Pattern Recognition · Computer Science 2024-12-04 Leah Bar , Boaz Lerner , Nir Darshan , Rami Ben-Ari

Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty-aware data selection methods attempt to address this by…

Machine Learning · Computer Science 2026-05-12 Yang Zhou , Can Jin , Zihan Dong , Zhepeng Wang , Yanting Yang , Shiyu Zhao , Lei Li , Runxue Bao , Yaochen Xie , Dimitris N. Metaxas

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to uncover informative learning signals for difficult prompts.…

Machine Learning · Computer Science 2025-12-08 Wei Xiong , Chenlu Ye , Baohao Liao , Hanze Dong , Xinxing Xu , Christof Monz , Jiang Bian , Nan Jiang , Tong Zhang

Decentralized large language model inference networks require lightweight mechanisms to reward high quality outputs under heterogeneous latency and cost. Proof of Quality provides scalable verification by sampling evaluator nodes that score…

Cryptography and Security · Computer Science 2026-01-30 Arther Tian , Alex Ding , Frank Chen , Simon Wu , Aaron Chan

Deep predictive models rely on human supervision in the form of labeled training data. Obtaining large amounts of annotated training data can be expensive and time consuming, and this becomes a critical bottleneck while building such models…

Machine Learning · Statistics 2020-10-01 Bindya Venkatesh , Jayaraman J. Thiagarajan

Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans) or limited in utility (e.g., tools like Lean). While LM…

Ranking and selection (R&S) aims to identify the alternative with the best mean performance among $k$ simulated alternatives. The practical value of R&S depends on accurate simulation input modeling, which often suffers from the curse of…

Machine Learning · Statistics 2025-09-09 Zaile Li , Yuchen Wan , L. Jeff Hong

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…

Computation and Language · Computer Science 2018-12-11 Ziming Li , Julia Kiseleva , Maarten de Rijke

In human-in-the-loop reinforcement learning or environments where calculating a reward is expensive, the costly rewards can make learning efficiency challenging to achieve. The cost of obtaining feedback from humans or calculating expensive…

Machine Learning · Computer Science 2025-03-03 Muhammed Yusuf Satici , David L. Roberts

Most machine learning and data analytics applications, including performance engineering in software systems, require a large number of annotations and labelled data, which might not be available in advance. Acquiring annotations often…

Software Engineering · Computer Science 2023-09-21 Peter Samoaa , Linus Aronsson , Antonio Longa , Philipp Leitner , Morteza Haghir Chehreghani

Past work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first tag training stories with the…

Computation and Language · Computer Science 2020-10-08 Harsh Jhamtani , Taylor Berg-Kirkpatrick

Retrieval augmented generation (RAG) reduces hallucinations and factual errors in large language models (LLMs) by conditioning generation on retrieved external knowledge. Recent search agents further cast RAG as an autonomous, multi-turn…

Computation and Language · Computer Science 2026-03-05 Jian Li , Yizhang Jin , Dongqi Liu , Hang Ding , Jiafu Wu , Dongsheng Chen , Yunhang Shen , Yulei Qin , Ying Tai , Chengjie Wang , Xiaotong Yuan , Yabiao Wang

Despite large incentives, ecorrectness in software remains an elusive goal. Declarative programming techniques, where algorithms are derived from a specification of the desired behavior, offer hope to address this problem, since there is a…

Programming Languages · Computer Science 2018-01-22 Anthony Di Franco

We present a method for active inference with partial observations in stochastic systems through incentive design, also known as the leader-follower game. Consider a leader agent who aims to infer a follower agent's type given a finite set…

Systems and Control · Electrical Eng. & Systems 2025-02-12 Xinyi Wei , Chongyang Shi , Shuo Han , Ahmed H. Hemida , Charles A. Kamhoua , Jie Fu

Modern preference alignment techniques, such as Best-of-N (BoN) sampling, rely on reward models trained with pairwise comparison data. While effective at learning relative preferences, this paradigm fails to capture a signal of response…

Methodology · Statistics 2025-10-14 Hyung Gyu Rho , Sian Lee

Reinforcement learning algorithms in multi-agent systems deliver highly resilient and adaptable solutions for common problems in telecommunications,aerospace, and industrial robotics. However, achieving an optimal global goal remains a…

Multiagent Systems · Computer Science 2021-05-18 Changgang Zheng , Shufan Yang , Juan Parra-Ullauri , Antonio Garcia-Dominguez , Nelly Bencomo

This study presents a generative optimization framework that builds on a fine-tuned diffusion model and reward-directed sampling to generate high-performance engineering designs. The framework adopts a parametric representation of the…

Machine Learning · Computer Science 2025-08-05 Hadi Keramati , Patrick Kirchen , Mohammed Hannan , Rajeev K. Jaiman

We propose a learning setting in which unlabeled data is free, and the cost of a label depends on its value, which is not known in advance. We study binary classification in an extreme case, where the algorithm only pays for negative…

Machine Learning · Computer Science 2015-07-14 Sivan Sabato , Anand D. Sarwate , Nathan Srebro

Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure. However, practical deployments face two persistent…

Information Retrieval · Computer Science 2026-01-30 Jiate Liu , Zebin Chen , Shaobo Qiao , Mingchen Ju , Danting Zhang , Bocheng Han , Shuyue Yu , Xin Shu , Jingling Wu , Dong Wen , Xin Cao , Guanfeng Liu , Zhengyi Yang

We show that, under a standard hardness assumption, there is no computationally efficient algorithm that given $n$ samples from an unknown distribution can give valid answers to $n^{3+o(1)}$ adaptively chosen statistical queries. A…

Machine Learning · Computer Science 2014-08-08 Moritz Hardt , Jonathan Ullman