English
Related papers

Related papers: Co-Evolving LLM Coder and Unit Tester via Reinforc…

200 papers

Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in tasks requiring complex multi-step reasoning. While dense…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure the robustness of the reasoning process itself. We adopt a…

Machine Learning · Computer Science 2026-02-10 Hyunseok Lee , Soheil Abbasloo , Jihoon Tack , Jinwoo Shin

Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…

Computation and Language · Computer Science 2026-03-17 Yu Liu , Wenxiao Zhang , Diandian Guo , Cong Cao , Fangfang Yuan , Qiang Sun , Yanbing Liu , Jin B. Hong , Zhiyuan Ma

We present Dream-Coder 7B, an open-source discrete diffusion language model for code generation that exhibits emergent any-order generation capabilities. Unlike traditional autoregressive (AR) models that decode strictly left-to-right,…

Computation and Language · Computer Science 2025-09-03 Zhihui Xie , Jiacheng Ye , Lin Zheng , Jiahui Gao , Jingwei Dong , Zirui Wu , Xueliang Zhao , Shansan Gong , Xin Jiang , Zhenguo Li , Lingpeng Kong

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most…

Computation and Language · Computer Science 2024-03-19 Wendi Li , Wei Wei , Kaihe Xu , Wenfeng Xie , Dangyang Chen , Yu Cheng

With the recent advancement of Large Language Models (LLMs), generating functionally correct code has become less complicated for a wide array of developers. While using LLMs has sped up the functional development process, it poses a heavy…

Cryptography and Security · Computer Science 2024-02-01 Nafis Tanveer Islam , Mohammad Bahrami Karkevandi , Peyman Najafirad

Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While it may improve accuracy, we observe it…

Computation and Language · Computer Science 2025-10-13 Jiuheng Lin , Cong Jiang , Zirui Wu , Jiarui Sun , Yansong Feng

Recent advances of Reinforcement Learning (RL) have highlighted its potential in complex reasoning tasks, yet effective training often relies on external supervision, which limits the broader applicability. In this work, we propose a novel…

Artificial Intelligence · Computer Science 2025-06-11 Kongcheng Zhang , Qi Yao , Shunyu Liu , Yingjie Wang , Baisheng Lai , Jieping Ye , Mingli Song , Dacheng Tao

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Machine Learning · Computer Science 2025-10-31 Fuxiang Zhang , Jiacheng Xu , Chaojie Wang , Ce Cui , Yang Liu , Bo An

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a prevailing paradigm for enhancing reasoning in Multimodal Large Language Models (MLLMs). However, relying solely on outcome supervision risks reward hacking, where…

Computation and Language · Computer Science 2026-03-04 Yukun Chen , Jiaming Li , Longze Chen , Ze Gong , Jingpeng Li , Zhen Qin , Hengyu Chang , Ancheng Xu , Zhihao Yang , Hamid Alinejad-Rokny , Qiang Qu , Bo Zheng , Min Yang

Reinforcement learning (RL) to improve code review comment generation requires handling unstructured outputs, making reinforcement learning (RL) feedback challenging. The two main RL approaches, namely RL with Verifiable Feedback (RLVR) and…

Software Engineering · Computer Science 2025-06-03 Manav Nitin Kapadnis , Atharva Naik , Carolyn Rose

We propose STRuCT-LLM, a unified framework for training large language models (LLMs) to perform structured reasoning over both relational and graph-structured data. Our approach jointly optimizes Text-to-SQL and Text-to-Cypher tasks using…

Computation and Language · Computer Science 2025-06-30 Josefa Lia Stoisser , Marc Boubnovski Martell , Lawrence Phillips , Casper Hansen , Julien Fauqueur

Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homogeneous solutions. In such environments, the lack of failure…

Machine Learning · Computer Science 2026-04-21 Zhenwen Liang , Yujun Zhou , Sidi Lu , Xiangliang Zhang , Haitao Mi , Dong Yu

Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield black-box models that are difficult to interpret and debug. In this work, we introduce GRACE (Generating Rewards As…

Machine Learning · Computer Science 2026-01-29 Silvia Sapora , Devon Hjelm , Alexander Toshev , Omar Attia , Bogdan Mazoure

Recent advances in large language models (LLMs) have demonstrated that reinforcement learning with verifiable rewards (RLVR) can significantly enhance reasoning abilities by directly optimizing correctness, rather than relying solely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Minbin Huang , Runhui Huang , Chuanyang Zheng , Jingyao Li , Guoxuan Chen , Han Shi , Hong Cheng

Enhancing the reasoning capabilities of large language models (LLMs) typically relies on massive computational resources and extensive datasets, limiting accessibility for resource-constrained settings. Our study investigates the potential…

Machine Learning · Computer Science 2026-01-21 Quy-Anh Dang , Chris Ngo

The goal of program synthesis, or code generation, is to generate executable code based on given descriptions. Recently, there has been an increasing number of studies employing reinforcement learning (RL) to improve the performance of…

Artificial Intelligence · Computer Science 2023-11-14 Jiate Liu , Yiqin Zhu , Kaiwen Xiao , Qiang Fu , Xiao Han , Wei Yang , Deheng Ye

Reinforcement learning from verifiable rewards (RLVR) has recently gained attention for its ability to elicit self-evolved reasoning capabilitie from base language models without explicit reasoning supervisions, as demonstrated by…

Computation and Language · Computer Science 2025-02-28 Sheng Zhang , Qianchu Liu , Guanghui Qin , Tristan Naumann , Hoifung Poon

This paper introduces a novel code-to-code search technique that enhances the performance of Large Language Models (LLMs) by including both static and dynamic features as well as utilizing both similar and dissimilar examples during…

Software Engineering · Computer Science 2024-04-17 Anthony Saieva , Saikat Chakraborty , Gail Kaiser

Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement learning from verifiable rewards (RLVR) has advanced in other…