English
Related papers

Related papers: Evolving Language Models without Labels: Majority …

200 papers

Post-training large language models with reinforcement learning is bottlenecked by the reward signal. Existing approaches require either ground-truth verifiable rewards, restricting training to domains with automatic correctness checks…

Machine Learning · Computer Science 2026-05-29 Matt Gorbett , Hossein Shirazi

The rapid advancement of Large Language Models (LLMs) poses a significant challenge to existing mathematical reasoning benchmarks. However, these benchmarks tend to become easier over time as LLMs can learn from the published benchmarks.…

Artificial Intelligence · Computer Science 2025-10-07 Shengbo Wang , Mingwei Liu , Zike Li , Anji Li , Yanlin Wang , Xin Peng , Zibin Zheng

Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to improve bounds on open problems. However, it relies on…

Test-time scaling has emerged as a promising direction for enhancing the reasoning capabilities of Large Language Models in last few years. In this work, we propose Population-Evolve, a training-free method inspired by Genetic Algorithms to…

Artificial Intelligence · Computer Science 2025-12-23 Yanzhi Zhang , Yitong Duan , Zhaoxi Zhang , Jiyan He , Shuxin Zheng

Recent advancements in Large Language Models have yielded significant improvements in complex reasoning tasks such as mathematics and programming. However, these models remain heavily dependent on annotated data and exhibit limited…

Machine Learning · Computer Science 2025-09-01 Jia Liu , ChangYi He , YingQiao Lin , MingMin Yang , FeiYang Shen , ShaoGuo Liu

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

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…

Machine Learning · Computer Science 2025-05-22 Shivam Agarwal , Zimin Zhang , Lifan Yuan , Jiawei Han , Hao Peng

Reinforcement learning with verifiable rewards (RLVR) has proven effective in training large reasoning models (LRMs) by leveraging answer-verifiable signals to guide policy optimization, which, however, suffers from high annotation costs.…

Machine Learning · Computer Science 2025-12-16 Shenzhi Yang , Guangcheng Zhu , Xing Zheng , Yingfan MA , Zhongqi Chen , Bowen Song , Weiqiang Wang , Junbo Zhao , Gang Chen , Haobo Wang

Self-evolution of multimodal large language models (MLLMs) remains a critical challenge: pseudo-label-based methods suffer from progressive quality degradation as model predictions drift, while template-based methods are confined to a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Yongrui Heng , Chaoya Jiang , Han Yang , Shikun Zhang , Wei Ye

Reinforcement learning with human-annotated data has boosted chain-of-thought reasoning in large reasoning models, but these gains come at high costs in labeled data while faltering on harder tasks. A natural next step is experience-driven…

Computation and Language · Computer Science 2025-10-03 Zhaoning Yu , Will Su , Leitian Tao , Haozhu Wang , Aashu Singh , Hanchao Yu , Jianyu Wang , Hongyang Gao , Weizhe Yuan , Jason Weston , Ping Yu , Jing Xu

Current alignment methods for Large Language Models (LLMs) rely on compressing vast amounts of human preference data into static, absolute reward functions, leading to data scarcity, noise sensitivity, and training instability. We introduce…

Computation and Language · Computer Science 2026-03-03 Jing Zhao , Ting Zhen , Junwei Bao , Hongfei Jiang , Yang Song

Large language models (LLMs) face significant challenges in effectively leveraging sequential environmental feedback (EF) signals, such as natural language evaluations, for feedback-independent chain-of-thought (CoT) reasoning. Existing…

Computation and Language · Computer Science 2025-07-29 Kang Yang , Jingxue Chen , Qingkun Tang , Tianxiang Zhang , Qianchun Lu

Improving the code generation capabilities of large language models (LLMs) typically relies on supervised fine-tuning or preference optimization, both of which require costly external resources such as powerful teacher models or reliable…

Software Engineering · Computer Science 2026-04-01 Huan Zhang , Wei Cheng , Wei Hu

Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from human feedback has been successful in aligning agents with…

Machine Learning · Computer Science 2025-06-17 Tung Minh Luu , Younghwan Lee , Donghoon Lee , Sunho Kim , Min Jun Kim , Chang D. Yoo

Verilog's design cycle is inherently labor-intensive and necessitates extensive domain expertise. Although Large Language Models (LLMs) offer a promising pathway toward automation, their limited training data and intrinsic sequential…

Artificial Intelligence · Computer Science 2026-01-27 Wei-Po Hsin , Ren-Hao Deng , Yao-Ting Hsieh , En-Ming Huang , Shih-Hao Hung

Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision for post-training. Such supervision is costly to obtain,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Chaoran Xu , Yingmao Miao , Pengfei Zhang , Hao Dou , Lei Sun , Xiangxiang Chu

We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of adapting model…

Machine Learning · Computer Science 2026-05-15 Weijia Xu , Alessandro Sordoni , Chandan Singh , Zelalem Gero , Michel Galley , Xingdi Yuan , Jianfeng Gao

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models. However, existing methods rely solely on outcome rewards, without explicitly optimizing verification or leveraging…

Software Engineering · Computer Science 2025-10-22 Yiyang Jin , Kunzhao Xu , Hang Li , Xueting Han , Yanmin Zhou , Cheng Li , Jing Bai

While combining large language models (LLMs) with evolutionary algorithms (EAs) shows promise for solving complex optimization problems, current approaches typically evolve individual solutions, often incurring high LLM call costs. We…

Artificial Intelligence · Computer Science 2025-08-12 Yi Zhai , Zhiqiang Wei , Ruohan Li , Keyu Pan , Shuo Liu , Lu Zhang , Jianmin Ji , Wuyang Zhang , Yu Zhang , Yanyong Zhang

Large language models can answer causal questions correctly for the wrong reasons. Current RL methods reward \emph{what} a model concludes but ignore \emph{why}, reinforcing correlational shortcuts -- a failure we call \emph{Reward…

Artificial Intelligence · Computer Science 2026-05-21 Edward Y. Chang , Longling Geng