English
Related papers

Related papers: Rewarding Progress: Scaling Automated Process Veri…

200 papers

Generative Reward Models (GRMs) provide greater flexibility than scalar reward models in capturing human preferences, but their effectiveness is limited by poor reasoning capabilities. This often results in incomplete or overly speculative…

Computation and Language · Computer Science 2025-06-23 Bin Chen , Xinzge Gao , Chuanrui Hu , Penghang Yu , Hua Zhang , Bing-Kun Bao

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

Computation and Language · Computer Science 2024-03-29 Hao Lang , Fei Huang , Yongbin Li

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by…

Artificial Intelligence · Computer Science 2025-11-25 Jaewoo Lee , Archiki Prasad , Justin Chih-Yao Chen , Zaid Khan , Elias Stengel-Eskin , Mohit Bansal

Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), as it reflects their ability to derive valid conclusions from given premises. While the combination of test-time scaling with…

Computation and Language · Computer Science 2025-08-28 Ramya Keerthy Thatikonda , Wray Buntine , Ehsan Shareghi

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Computation and Language · Computer Science 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang

Mathematical theorem proving is an important testbed for large language models' deep and abstract reasoning capability. This paper focuses on improving LLMs' ability to write proofs in formal languages that permit automated proof…

Machine Learning · Computer Science 2024-11-05 Kefan Dong , Arvind Mahankali , Tengyu Ma

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group…

Machine Learning · Computer Science 2026-04-23 Jingyi Wang , Lei Zhu , Tengjin Weng , Song-Li Wu , Haochen Tan , Jierun Chen , Chaofan Tao , Haoli Bai , Lu Hou , Lifeng Shang , Xiao-Ping Zhang

Process-Level Reward Models (PRMs) are essential for guiding complex reasoning in large language models, yet existing PRM benchmarks cover only general domains such as mathematics, failing to address medical reasoning -- which is uniquely…

Computation and Language · Computer Science 2026-04-21 Lingyan Wu , Xiang Zheng , Weiqi Zhai , Wei Wang , Xuan Ren , Zifan Zhang , Hu Wei , Bing Zhao

This paper investigates Reinforcement Learning (RL) approaches to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-horizon, multi-turn scenarios. Although RL algorithms such as Group Relative Policy…

While chain-of-thought prompting with Best-of-N (BoN) selection has become popular for mathematical reasoning in large language models (LLMs), its linear structure fails to capture the branching and exploratory nature of complex…

Machine Learning · Computer Science 2025-10-24 Tristan Cinquin , Geoff Pleiss , Agustinus Kristiadi

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks,…

Computation and Language · Computer Science 2025-10-30 Ziyou Hu , Zhengliang Shi , Minghang Zhu , Haitao Li , Teng Sun , Pengjie Ren , Suzan Verberne , Zhaochun Ren

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

Reinforcement Learning (RL) serves as a potent paradigm for enhancing reasoning capabilities in Large Language Models (LLMs), yet standard outcome-based approaches often suffer from reward sparsity and inefficient credit assignment. In this…

Artificial Intelligence · Computer Science 2026-02-03 Xiangwei Wang , Wei Wang , Ken Chen , Nanduni Nimalsiri , Saman Halgamuge

In recent years, large language models have greatly improved in their ability to perform complex multi-step reasoning. However, even state-of-the-art models still regularly produce logical mistakes. To train more reliable models, we can…

Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. However, we identify a pervasive length bias in existing PRMs:…

Computation and Language · Computer Science 2026-05-20 Congmin Zheng , Jiachen Zhu , Jianghao Lin , Xinyi Dai , Weiwen Liu , Haoxuan Li , Yong Yu , Weinan Zhang , Mengyue Yang

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

Machine Learning · Computer Science 2025-07-31 Zijing Zhang , Ziyang Chen , Mingxiao Li , Zhaopeng Tu , Xiaolong Li

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same…

Machine Learning · Computer Science 2025-04-29 Zhaoyang Wang , Weilei He , Zhiyuan Liang , Xuchao Zhang , Chetan Bansal , Ying Wei , Weitong Zhang , Huaxiu Yao

Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved information, with no clear or…

Information Retrieval · Computer Science 2026-04-10 Roxana Petcu , Evangelos Kanoulas , Maarten de Rijke

Process reward models (PRMs) enhance complex reasoning in large language models (LLMs) by evaluating candidate solutions step-by-step and selecting answers based on aggregated step scores. While effective in domains such as mathematics,…

Computation and Language · Computer Science 2026-01-26 Lei Tang , Wei Zhou , Mohsen Mesgar