System prompt optimization improves agent behavior without modifying the underlying model, yielding human-readable, model-agnostic instructions. Existing methods build a prompt agent that refines task agents' system prompts, yet leave the prompt agent's own system prompt hand-engineered and fixed. We propose Self-Evolving Prompt Optimization (SePO), which treats the prompt agent's own system prompt as an optimization target alongside task agents' system prompts. SePO adopts a self-referential design. A single prompt agent improves both task agents' system prompts and its own under an open-ended evolutionary search that maintains an archive of candidate prompts as stepping stones. Training proceeds in two stages: pre-training evolves the prompt agent on a multi-task pool, and fine-tuning then applies it to a target task. Across five benchmarks spanning math (AIME'25), abstract reasoning (ARC-AGI-1), graduate-level science (GPQA), code generation (MBPP), and logic puzzles (Sudoku), SePO consistently outperforms Manual-CoT, TextGrad, and MetaSPO, improving the average accuracy by 4.49 points compared to Manual-CoT. The prompt optimization skill from pre-training also generalizes to tasks beyond the pre-training mixture, rather than memorizing per-task prompts.
Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
University of California, Los Angeles（加州大学洛杉矶分校）；Georgia Institute of Technology（佐治亚理工学院）；University of Chicago（芝加哥大学）；University of Oxford（牛津大学）；Ludwig-Maximilians-Universität München（慕尼黑大学）；Yale University（耶鲁大学）
From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shanghai AI Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；New Jersey Institute of Technology（新泽西理工学院）
SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning
School of Computing Science, University of Glasgow（格拉斯哥大学计算科学学院）；Brigham and Women’s Hospital, Harvard Medical School, Harvard University（哈佛大学医学院附属布莱根妇女医院）；Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）；School of Natural and Computing Science, University of Aberdeen（阿伯丁大学自然与计算科学学院）；School of Cancer Sciences, University of Glasgow（格拉斯哥大学癌症科学学院）；Cancer Research UK Scotland Institute（英国癌症研究苏格兰研究所）
Towards Verifiable Text Generation with Evolving Memory and Self-Reflection
State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室）；School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；Chinese Academy of Sciences（中国科学院）；Beijing Institute of Technology（北京理工大学）；Baidu Inc（百度公司）
Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed Bandits
University of Notre Dame（诺丁汉大学）；Northeastern University（东北大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Southeast University（东南大学）；Northwestern University（西北大学）；Nanjing University（南京大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring
Korea University Sejong Campus（韩国大学世宗校区）；Gyeonggi Institute of Education（京畿教育学院）；Indiana University Bloomington（印第安纳大学布卢明顿分校）；Opentutorials；Chosun University（全州大学）；Korea University Korean Studies Center（韩国大学韩学研究中心）
