English
Related papers

Related papers: SAGE: Multi-Agent Self-Evolution for LLM Reasoning

200 papers

Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These…

The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). While DeepSeek-R1 and other follow-up work primarily focus…

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

In recent years, large language models (LLMs) have demonstrated strong performance on multilingual tasks. Given its wide range of applications, cross-cultural understanding capability is a crucial competency. However, existing benchmarks…

Computation and Language · Computer Science 2025-12-09 Shiwei Guo , Sihang Jiang , Qianxi He , Yanghua Xiao , Jiaqing Liang , Bi Yude , Minggui He , Shimin Tao , Li Zhang

Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often…

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

Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete…

Machine Learning · Computer Science 2022-03-11 Andrew Chester , Michael Dann , Fabio Zambetta , John Thangarajah

Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…

Machine Learning · Computer Science 2025-09-04 Sherry Yang , Joy He-Yueya , Percy Liang

Large Language Models (LLMs) exhibit strong potential in mathematical reasoning, yet their effectiveness is often limited by a shortage of high-quality queries. This limitation necessitates scaling up computational responses through…

Artificial Intelligence · Computer Science 2025-05-20 Jingyue Gao , Runji Lin , Keming Lu , Bowen Yu , Junyang Lin , Jianyu Chen

Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools. We…

Artificial Intelligence · Computer Science 2025-05-20 Maxime Robeyns , Martin Szummer , Laurence Aitchison

Large language models (LLMs) make it plausible to build systems that improve through self-evolving loops, but many existing proposals are better understood as self-play and often plateau quickly. A central failure mode is that the loop…

Machine Learning · Computer Science 2026-05-19 Wei Liu , Siya Qi , Yali Du , Yulan He

Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward…

Machine Learning · Computer Science 2025-12-09 Zhicheng Cai , Xinyuan Guo , Yu Pei , Jiangtao Feng , Jinsong Su , Jiangjie Chen , Ya-Qin Zhang , Wei-Ying Ma , Mingxuan Wang , Hao Zhou

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…

Artificial Intelligence · Computer Science 2025-10-31 Xiaoyin Chen , Jiarui Lu , Minsu Kim , Dinghuai Zhang , Jian Tang , Alexandre Piché , Nicolas Gontier , Yoshua Bengio , Ehsan Kamalloo

Large Language Models (LLMs) have made remarkable breakthroughs in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during complex multi-step tasks. Current approaches like…

Computation and Language · Computer Science 2025-04-22 Lingrui Mei , Shenghua Liu , Yiwei Wang , Baolong Bi , Yuyao Ge , Jun Wan , Yurong Wu , Xueqi Cheng

The quest for expert-level reasoning in Large Language Models (LLMs) has been hampered by a persistent \textit{reward bottleneck}: traditional reinforcement learning (RL) relies on scalar rewards that are \textbf{costly} to scale,…

Artificial Intelligence · Computer Science 2026-05-25 Yiwen Duan , Jing Ye , Xinpei Zhao

Small language models (SLMs) offer compelling advantages in cost, latency, and adaptability, but have so far lagged behind larger models on long-horizon software engineering tasks such as SWE-bench, where they suffer from pervasive action…

Software Engineering · Computer Science 2026-02-26 Patrick Tser Jern Kon , Archana Pradeep , Ang Chen , Alexander P. Ellis , Warren Hunt , Zijian Wang , John Yang , Samuel Thompson

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 have evolved from single-round generators into long-horizon agents, capable of complex text synthesis scenarios. However, current evaluation frameworks lack the ability to assess the actual synthesis operations, such…

Computation and Language · Computer Science 2026-03-03 Andrew Zhuoer Feng , Cunxiang Wang , Yu Luo , Bosi Wen , Yidong Wang , Lin Fan , Yilin Zhou , Zikang Wang , Wenbo Yu , Lindong Wu , Hongning Wang , Minlie Huang

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic…

Computation and Language · Computer Science 2026-02-10 Weixiang Zhao , Yingshuo Wang , Yichen Zhang , Yang Deng , Yanyan Zhao , Wanxiang Che , Bing Qin , Ting Liu

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…

Artificial Intelligence · Computer Science 2026-05-22 Mingkai Deng , Jinyu Hou , Lara Sá Neves , Varad Pimpalkhute , Taylor W. Killian , Zhengzhong Liu , Eric P. Xing

Large language models (LLMs) excel at natural language tasks but are limited by their static parametric knowledge, especially in knowledge-intensive task. Retrieval-augmented generation (RAG) mitigates this by integrating external…

Artificial Intelligence · Computer Science 2025-10-10 Yi Jiang , Lei Shen , Lujie Niu , Sendong Zhao , Wenbo Su , Bo Zheng