English
Related papers

Related papers: Stabilizing Iterative Self-Training with Verified …

200 papers

This paper presents a novel RL algorithm, S-REINFORCE, which is designed to generate interpretable policies for dynamic decision-making tasks. The proposed algorithm leverages two types of function approximators, namely Neural Network (NN)…

Machine Learning · Computer Science 2023-05-15 Rajdeep Dutta , Qincheng Wang , Ankur Singh , Dhruv Kumarjiguda , Li Xiaoli , Senthilnath Jayavelu

Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning gains, but collapse and instability are widely observed and…

Machine Learning · Computer Science 2026-05-22 Sophia Xiao Pu , Zhaotian Weng , Chengzhi Liu , Jayanth Srinivasa , Gaowen Liu , William Yang Wang , Xin Eric Wang

Neural Module Networks (NMNs) have been quite successful in incorporating explicit reasoning as learnable modules in various question answering tasks, including the most generic form of numerical reasoning over text in Machine Reading…

Computation and Language · Computer Science 2021-01-29 Amrita Saha , Shafiq Joty , Steven C. H. Hoi

In this work we introduce a structured signaling game, an extension of the classical signaling game with a similarity structure between meanings in the context, along with a variant of the Rational Speech Act (RSA) framework which we call…

Artificial Intelligence · Computer Science 2023-05-18 Emil Carlsson , Devdatt Dubhashi

Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficiency and accuracy:…

Computation and Language · Computer Science 2026-03-24 Yuran Li , Di Wu , Benoit Boulet

This report extends the Spectral Neuro-Symbolic Reasoning (Spectral NSR) framework by introducing three semantically grounded enhancements: (1) transformer-based node merging using contextual embeddings (e.g., Sentence-BERT, SimCSE) to…

Computation and Language · Computer Science 2025-11-17 Andrew Kiruluta , Priscilla Burity

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Artificial Intelligence · Computer Science 2026-01-30 Zhao Wang , Ziliang Zhao , Zhicheng Dou

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

Speculative reasoning has recently been proposed as a means to accelerate reasoning-intensive generation in large multimodal models, but its effectiveness is often constrained by misalignment between speculative drafts and target-verified…

Artificial Intelligence · Computer Science 2026-05-28 Yunhai Hu , Zining Liu , Xiangyang Yin , Tianhua Xia , Bo Bao , Eric Sather , Vithursan Thangarasa , Sai Qian Zhang

Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to model reasoning trajectories with a latent dynamical system. We argue that the…

Artificial Intelligence · Computer Science 2026-05-28 Andrew Corbett , Archit Sood , Anna Tzatzopoulou , Sai-Aakash Ramesh , Tim Dodwell

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Machine Learning · Computer Science 2026-02-20 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Hao Sun , Chenliang Xu , Jianfeng Gao

Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging…

Computation and Language · Computer Science 2023-10-27 Yuxi Xie , Kenji Kawaguchi , Yiran Zhao , Xu Zhao , Min-Yen Kan , Junxian He , Qizhe Xie

Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference, but its success hinges on constructing reliable learning signals. Standard approaches such as majority…

Computation and Language · Computer Science 2026-03-03 Ru Wang , Wei Huang , Qi Cao , Yusuke Iwasawa , Yutaka Matsuo , Jiaxian Guo

Large Language Models (LLMs) are increasingly deployed in critical applications requiring reliable reasoning, yet their internal reasoning processes remain difficult to evaluate systematically. Existing methods focus on final-answer…

Machine Learning · Computer Science 2026-02-03 Shaima Ahmad Freja , Ferhat Ozgur Catak , Betul Yurdem , Chunming Rong

Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two…

Machine Learning · Computer Science 2026-03-10 Jianyuan Zhong , Kaibo Wang , Ding Ding , Zijin Feng , Haoli Bai , Yang Xiang , Jiacheng Sun , Qiang Xu

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Computation and Language · Computer Science 2025-01-08 Yuchun Fan , Yongyu Mu , Yilin Wang , Lei Huang , Junhao Ruan , Bei Li , Tong Xiao , Shujian Huang , Xiaocheng Feng , Jingbo Zhu

Self-consistency methods are the core technique for improving the reasoning reliability of multimodal large language models (MLLMs). By generating multiple reasoning results through repeated sampling and selecting the best answer via…

Computation and Language · Computer Science 2026-02-05 Xinglong Yang , Zhilin Peng , Zhanzhan Liu , Haochen Shi , Sheng-Jun Huang

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

Reinforcement learning with verifiable rewards (RLVR) plays a pivotal role in improving the reasoning ability of large language models. However, widely used PPO surrogate objectives are fundamentally local, as they rely on a local…

Machine Learning · Computer Science 2026-05-21 Deokgyu Yoon , Hyungkyu Kang , Joongkyu Lee , Byeongchan Kim , Gyungin Shin , Sungrae Park , Min-hwan Oh

Reinforcement learning has become a central paradigm for advancing reasoning in large language models, yet most existing methods still depend on stronger teacher models or heavily curated difficult datasets, limiting scalable capability…

Artificial Intelligence · Computer Science 2026-05-28 Caijun Xu , Changyi Xiao , Zhongyuan Peng , Yixin Cao