1
20 余名行业领袖示警“智能爆炸”，Anthropic、OpenAI 高管呼吁关注 AI 自我改进
IT之家 9 月 29 日消息，据彭博社 28 日报道，Anthropic、OpenAI、Meta 和微软的高管共同敦促政策制定者，密切关注 AI 系统自我改进到了何种程度，并采取措施保障 AI 技术安全。 20 多名 AI 行业领袖和研究人员在一篇新论文中警告，利用 AI 推动下一代模型研发自动化…
2
AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement
首个面向递归自我改进的AI智能体算法设计基准，直击AI自我进化核心命题。
arXiv:2608.20318v1 Announce Type: cross Abstract: Recursive self-improvement (RSI) asks whether an AI system can improve the process that produces AI …
3
AI’s recursive self-improvement might not come so quickly after all
新研究给AI自我进化热潮泼冷水，揭秘“影子评估”为何更靠谱
The AI industry’s boldest promise right now is that AI will soon improve itself, with almost no need for human oversight. LLMs can already write code,…
4
Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
自我改进的LLM智能体会把成功轨迹固化为可复用技能，一次不安全的成功可能就此潜伏成系统风险。
arXiv:2608.12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state. An unsafe …
5
Exclusive: Mirendil inks $100M+ Google Cloud deal to scale self-improving AI
1亿美金牵手谷歌云，这家初创要让AI像科学家一样自我进化。
Mirendil has signed a $100 million-plus Google Cloud partnership to expand its compute infrastructure, powering research into self-improving AI system…
6
Causal Episodic Memory for Feedback-Driven Agent Repair
这项研究让AI智能体像人类一样记住失败教训，越用越聪明，快速自我修复不再重复犯错。
arXiv:2608.05906v1 Announce Type: new Abstract: LLM agents that repair failures often discard successful corrections, forcing later episodes to redisc…
7
Show HN: Wienerdog – memory and self-improving skills for Claude Code/Codex
跨工具共享的AI记忆库，让Claude Code与Codex无缝衔接，越用越懂你的偏好与历史。
The idea of Wienerdog was born out of my experience setting up my own simple but effective system of memory, self-improving skills and hooks for Claud…
8
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
LLM通过技能自我博弈与协同进化突破能力天花板，实现模型能力的自主提升与前沿拓展。
arXiv:2607.22529v1 Announce Type: new Abstract: LLM training is shifting from manual design and annotation to interaction-driven self-evolution. Howev…
9
When Claude Detects "Why Isn't This Fixed Yet?" and Repairs Its Own CLAUDE.md: A Self-Improvement Loop Driven by Frustration Signals in Transcripts
AI根据用户抱怨“怎么还没修好？”自动修复自己的配置文件，自我进化闭环太强了！
In a previous post , I extracted skill usage stats from my conversation logs. This time I'm going the other way: a weekly loop that reads the transcri…
10
腾讯混元发布科学发现智能体 Hyra，能够递归自我改进
腾讯混元推出递归自我改进的科研智能体Hyra，与DeepMind、Together AI等前沿进展对比，展现AI科学发现新突破
IT之家 7 月 21 日消息，腾讯混元今日推出 Hyra-1.0 ，这是 Hyra（Hunyuan Research Agent）的首个版本：一个能够递归自我改进、专为性能导向的研究与工程任务打造的智能体。 腾讯表示，除了公开基准，它还能在产品系统里，在真实的 AI 研发流水线上，在自然科学研究乃…
11
Enhancing LLMs through human feedback: a journey towards self-improvement
从人类反馈到大模型自我进化，看最新研究成果如何用反馈驱动LLM性能跃升。
arXiv:2607.11267v1 Announce Type: cross Abstract: In the rapidly evolving landscape of information retrieval systems, the ability to adapt and improve…
12
I Built a Self-Improving AI, and So Can You
用AI造AI不再是巨头专利，普通开发者也能入局，一文看懂自改进AI的实操路径。
Experiments in using AI to build AI show that the future doesn’t just belong to the frontier labs.
13
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
让LLM智能体像生物进化般自我迭代，双时间尺度元技能跃升带来真正的自主进化能力。
arXiv:2607.05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable pr…
14
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
让计算机代理从失败中自我进化，推理时实时改进，打破高质量轨迹数据瓶颈。
arXiv:2606.31270v1 Announce Type: cross Abstract: Computer-use agents, which leverage multimodal large language models (MLLMs) to operate computers an…
15
On the Convergence of Self-Improving Online LLM Alignment
揭示大语言模型在线自我改进对齐的收敛性理论，为LLM安全与性能优化提供数学基础，UAI 2026收录。
arXiv:2606.31524v1 Announce Type: cross Abstract: The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel for…
16
ISM:Self-Improving Strategy Memory for Continual Mathematical Reasoning
让大模型在数学推理中越用越聪明：ISM把解题策略沉淀为记忆库，实现持续自我进化，这是ICML数学工作坊的前沿探索。
arXiv:2606.31191v1 Announce Type: new Abstract: We propose Intelligent Schema Memory (ISM), a self-evolving memory-augmented system that improves math…
17
Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
用二元提问替代打分评判，让大模型评估更可解释，还能自我改进，值得研究。
arXiv:2606.27226v1 Announce Type: new Abstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexi…
18
OpenSIR: Open-Ended Self-Improving Reasoner
提出一种开放式自我改进推理器OpenSIR，通过自博弈突破标注数据限制，有望超越人类水平推理。
arXiv:2511.00602v3 Announce Type: replace Abstract: Recent advances in large language model (LLM) reasoning through reinforcement learning rely on ann…
19
AI coding agents can autonomously direct robot training
AI编码代理自主指导机器人训练，ENPIRE系统实现99%操作成功率，突破性自我改进策略
NVIDIA’s self-improvement program for robots enlists teams of AI coding agents.
20
Retrospective Progress-Aware Self-Refinement for LLM Agent Training
LLM智能体训练新突破：用回顾性进度感知自我改进，弥补元认知缺口，提升长程任务效果
arXiv:2606.14302v1 Announce Type: new Abstract: LLM-based agents trained with reinforcement learning optimize step-wise action prediction but lack met…