English
Related papers

Related papers: Self-Play Only Evolves When Self-Synthetic Pipelin…

200 papers

Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement, for example, by reconstructing datasets with refined…

Computation and Language · Computer Science 2025-10-28 Yongcheng Zeng , Xinyu Cui , Xuanfa Jin , Qirui Mi , Guoqing Liu , Zexu Sun , Mengyue Yang , Dong Li , Weiyu Ma , Ning Yang , Jian Zhao , Jianye Hao , Haifeng Zhang , Jun Wang

Large language models (LLMs) have advanced rapidly in recent years, driven by scale, abundant high-quality training data, and reinforcement learning. Yet this progress faces a fundamental bottleneck: the need for ever more data from which…

Artificial Intelligence · Computer Science 2025-12-22 Jakub Grudzien Kuba , Mengting Gu , Qi Ma , Yuandong Tian , Vijai Mohan , Jason Chen

We study two-level autoresearch for cooperation: an outer-loop AI agent autonomously redesigns the inner-loop pipeline of an LLM policy-synthesis system for multi-agent Sequential Social Dilemmas (SSDs). A researcher agent $\mathcal{R}$…

Multiagent Systems · Computer Science 2026-05-29 Víctor Gallego

Recent advancements in prompt engineering strategies, such as Chain-of-Thought (CoT) and Self-Discover, have demonstrated significant potential in improving the reasoning abilities of Large Language Models (LLMs). However, these…

Computation and Language · Computer Science 2024-10-15 Krishna Aswani , Huilin Lu , Pranav Patankar , Priya Dhalwani , Iris Tan , Jayant Ganeshmohan , Simon Lacasse

Recent large language models (LLMs) achieve strong performance in generating promising reasoning paths for complex tasks. However, despite powerful generation ability, LLMs remain weak at verifying their own answers, revealing a persistent…

Computation and Language · Computer Science 2026-02-10 Yuxin Chen , Yu Wang , Yi Zhang , Ziang Ye , Zhengzhou Cai , Yaorui Shi , Qi Gu , Hui Su , Xunliang Cai , Xiang Wang , An Zhang , Tat-Seng Chua

Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through…

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…

Computation and Language · Computer Science 2025-10-06 Hangfan Zhang , Siyuan Xu , Zhimeng Guo , Huaisheng Zhu , Shicheng Liu , Xinrun Wang , Qiaosheng Zhang , Yang Chen , Peng Ye , Lei Bai , Shuyue Hu

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

As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time…

Artificial Intelligence · Computer Science 2026-03-17 Minhua Lin , Hanqing Lu , Zhan Shi , Bing He , Rui Mao , Zhiwei Zhang , Zongyu Wu , Xianfeng Tang , Hui Liu , Zhenwei Dai , Xiang Zhang , Suhang Wang , Benoit Dumoulin , Jian Pei

Large language models (LLMs) have already revolutionized code generation, after being pretrained on publicly available code data. However, while various methods have been proposed to augment LLMs with retrieved knowledge and enhance the…

Computation and Language · Computer Science 2023-06-06 Shuyang Jiang , Yuhao Wang , Yu Wang

Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs). However, the success of RL for LLMs heavily relies on human-curated datasets and verifiable rewards,…

Artificial Intelligence · Computer Science 2025-10-31 Yixing Chen , Yiding Wang , Siqi Zhu , Haofei Yu , Tao Feng , Muhan Zhang , Mostofa Patwary , Jiaxuan You

Large Language Models (LLMs) are increasingly embedded in applications, and people can shape model behavior by editing prompt instructions. Yet encoding subtle, domain-specific policies into prompts is challenging. Although this process…

Human-Computer Interaction · Computer Science 2026-03-26 Minjae Lee , Minsuk Kahng

Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…

Artificial Intelligence · Computer Science 2026-01-13 Ping Guo , Chao Li , Yinglan Feng , Chaoning Zhang

Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from their own experiences. While existing frameworks mainly focus on mitigating external knowledge gaps,…

Computation and Language · Computer Science 2026-05-19 Rong Wu , Xiaoman Wang , Jianbiao Mei , Pinlong Cai , Daocheng Fu , Cheng Yang , Licheng Wen , Xuemeng Yang , Yufan Shen , Yuxin Wang , Botian Shi

Dynamical systems theory provides a framework for analyzing iterative processes and evolution over time. Within such systems, repetitive transformations can lead to stable configurations, known as attractors, including fixed points and…

Computation and Language · Computer Science 2025-05-19 Zhilin Wang , Yafu Li , Jianhao Yan , Yu Cheng , Yue Zhang

Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to…

Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation hinders further progress. While existing remedies such as…

Artificial Intelligence · Computer Science 2026-04-17 Zhuo Wang , Zhuo Zhang , Yafu Li , Yu Cheng , Lizhen Qu , Zenglin Xu

Self-play with large language models has emerged as a promising paradigm for achieving self-improving artificial intelligence. However, existing self-play frameworks often suffer from optimization instability, due to (i) non-stationary…

Artificial Intelligence · Computer Science 2026-01-22 Shengda Fan , Xuyan Ye , Yankai Lin

Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time, preventing genuine software evolution. This paper introduces self-evolving software…

Software Engineering · Computer Science 2026-05-01 Marco Robol , Paolo Giorgini

Augmenting Large Language Models (LLMs) with external tools enables them to execute complex, multi-step tasks. However, tool learning is hampered by the static synthetic data pipelines where data generation and model training are executed…

Computation and Language · Computer Science 2025-11-19 Kangning Zhang , Wenxiang Jiao , Kounianhua Du , Yuan Lu , Weiwen Liu , Weinan Zhang , Yong Yu