English
Related papers

Related papers: ZeroCoder: Can LLMs Improve Code Generation Withou…

200 papers

In this work, we study the problem of code generation with a large language model (LLM), with a focus on generating SQL queries from natural language questions. We ask: Instead of using supervised fine tuning with text-code pairs, can we…

Computation and Language · Computer Science 2025-06-09 Atharv Kulkarni , Vivek Srikumar

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs) by optimizing them against factual outcomes. However, this paradigm falters in long-context…

Computation and Language · Computer Science 2026-03-03 Guanzheng Chen , Michael Qizhe Shieh , Lidong Bing

Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, their effectiveness heavily relies on supervised training with extensive labeled (e.g., question-answering pairs) or unlabeled…

Computation and Language · Computer Science 2025-12-22 Jiajun Wu , Jian Yang , Wei Zhang , Lin Jing , Yuqing Ma , Ensheng Shi , Yuchi Ma , Zhoujun Li , Xianglong Liu

Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates. Yet high-quality test suites are scarce, existing datasets offer limited coverage, and static rewards fail to adapt as models improve. Recent…

Computation and Language · Computer Science 2026-03-17 Aozhe Wang , Yuchen Yan , Nan Zhou , Zhengxi Lu , Weiming Lu , Jun Xiao , Yueting Zhuang , Yongliang Shen

While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, they often produce solutions that lack guarantees of correctness, robustness, and efficiency. This limitation is particularly acute in domains…

Software Engineering · Computer Science 2025-09-04 Yueke Zhang , Yifan Zhang , Kevin Leach , Yu Huang

Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR intrinsically relies on ground-truth labels for reward…

Machine Learning · Computer Science 2026-05-26 Li Wang , Xiaodong Lu , Xiaohan Wang , Yikun Ban , Jiajun Chai , Wei Lin , Tianhao Peng , Guojun Yin

Visual reasoning is challenging, requiring both precise object grounding and understanding complex spatial relationships. Existing methods fall into two camps: language-only chain-of-thought approaches, which demand large-scale (image,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Damiano Marsili , Georgia Gkioxari

Recent advances such as DeepSeek R1-Zero highlight the effectiveness of incentive training, a reinforcement learning paradigm that computes rewards solely based on the final answer part of a language model's output, thereby encouraging the…

Computation and Language · Computer Science 2025-09-04 Wei Liu , Siya Qi , Xinyu Wang , Chen Qian , Yali Du , Yulan He

Reinforcement learning with verifiable rewards (RLVR) succeeds in reasoning tasks (e.g., math and code) by checking the final verifiable answer (i.e., a verifiable dot signal). However, extending this paradigm to open-ended generation is…

Computation and Language · Computer Science 2026-01-27 Yuxin Jiang , Yufei Wang , Qiyuan Zhang , Xingshan Zeng , Liangyou Li , Jierun Chen , Chaofan Tao , Haoli Bai , Lifeng Shang

Code generation aims to produce code that fulfills requirements written in natural languages automatically. Large language Models (LLMs) like ChatGPT have demonstrated promising effectiveness in this area. Nonetheless, these LLMs often fail…

Software Engineering · Computer Science 2025-01-15 Ruwei Pan , Hongyu Zhang , Chao Liu

Zero Reinforcement Learning (Zero-RL) has proven to be an effective approach for enhancing the reasoning capabilities of large language models (LLMs) by directly applying reinforcement learning with verifiable rewards on pretrained models,…

Artificial Intelligence · Computer Science 2025-10-30 Yuyuan Zeng , Yufei Huang , Can Xu , Qingfeng Sun , Jianfeng Yan , Guanghui Xu , Tao Yang , Fengzong Lian

Large language models (LLMs) have increasingly been applied to automatic programming code generation. This task can be viewed as a language generation task that bridges natural language, human knowledge, and programming logic. However, it…

Pre-trained large language models (LLMs) have significantly improved code generation. As these models scale up, there is an increasing need for the output to handle more intricate tasks and to be appropriately specialized to particular…

Machine Learning · Computer Science 2024-05-22 Xiangru Tang , Bill Qian , Rick Gao , Jiakang Chen , Xinyun Chen , Mark Gerstein

While Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising post-training paradigm for Large Language Models (LLMs), its dependency on the gold label or domain-specific verifiers limits its scalability to…

Machine Learning · Computer Science 2026-05-12 Xuexiang Wen , Hang Yu , Linchao Zhu , Gaoang Wang

Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has…

Software Engineering · Computer Science 2025-02-05 Yufan Ye , Ting Zhang , Wenbin Jiang , Hua Huang

Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs). However, it often relies on gold-standard answers or explicit evaluation…

Computation and Language · Computer Science 2026-03-03 Yao Xiao , Lei Wang , Yue Deng , Guanzheng Chen , Ziqi Jin , Jung-jae Kim , Xiaoli Li , Roy Ka-wei Lee , Lidong Bing

Large language models (LLMs) have been widely deployed in coding tasks, drawing increasing attention to the evaluation of the quality and safety of LLMs' outputs. However, research on bias in code generation remains limited. Existing…

Computation and Language · Computer Science 2025-04-03 Yongkang Du , Jen-tse Huang , Jieyu Zhao , Lu Lin

Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR approaches typically rely on outcome-driven optimization that…

Artificial Intelligence · Computer Science 2026-04-10 Ziqi Miao , Haonan Jia , Lijun Li , Chen Qian , Yuan Xiong , Wenting Yan , Jing Shao

Training LLMs for code-related tasks typically depends on high-quality code-documentation pairs, which are costly to curate and often scarce for niche programming languages. We introduce BatCoder, a self-supervised reinforcement learning…

The recent paradigm shift towards training large language models (LLMs) using DeepSeek-R1-Zero-style reinforcement learning (RL) on verifiable rewards has led to impressive advancements in code and mathematical reasoning. However, this…

Machine Learning · Computer Science 2025-05-28 Xiangxin Zhou , Zichen Liu , Anya Sims , Haonan Wang , Tianyu Pang , Chongxuan Li , Liang Wang , Min Lin , Chao Du