1
智谱 GLM 公开国内大模型首个递归自我改进实践：AI 在十万卡国产集群上自建推理系统
IT之家 9 月 17 日消息，今日，智谱 GLM 团队披露递归自我改进（Recursive Self‑Improvement，简称 RSI）方向首个工程化实践进展，也就是让 AI 自己动手改进自己的运行系统。 具体来说，由 GLM-5.3 驱动的 Infra Agent 完成了 GLM-5.3-F…
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
How the Internet Finds Its Way: A Guide to DNS Resolution
用打电话通讯录的类比，把DNS解析从递归查询到缓存机制讲得通俗易懂，适合想搞懂域名背后原理的开发者。
Have you ever wondered how typing a few letters into your browser magically brings up your favorite website in milliseconds? This seamless connection …
5
Recursive Synthesis for Long-Horizon Terminal Tasks
面向长时程终端任务，递归合成方法带来全新解决思路，值得关注。
arXiv:2608.05466v1 Announce Type: new Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hun…
6
Chained Recursive Language Models for Multi-Iteration Reasoning
探索链式递归语言模型如何突破单次推理限制，实现多迭代深度思考，为复杂推理任务提供新范式。
arXiv:2608.05124v1 Announce Type: cross Abstract: Long context reasoning in large language models (LLMs) is usually constrained by the fact that a sin…
7
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…
8
Extending LLM Context via Associative Recurrent Memory
提出关联递归记忆方法，让大模型上下文窗口突破长度限制，高效处理超长序列
arXiv:2607.11614v1 Announce Type: cross Abstract: Extending the context length of large language models (LLMs) is critical for many real-world applica…
9
ReCoLoRA: Spectrum-Aware Recursive Consolidation for Continual LLM Fine-Tuning
突破LLM持续微调遗忘瓶颈，ReCoLoRA以频谱感知递归合并实现任务序列高效学习。
arXiv:2607.07719v1 Announce Type: new Abstract: Parameter-efficient fine-tuning adapts a large language model to one task cheaply, but across a task s…
10
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…
11
Recursive Entropic Variational Inference for Nonlinear State-Space Models
非线性状态空间模型遇上递归熵变分推断，新方法突破复杂概率推理难题。
arXiv:2511.15409v2 Announce Type: replace Abstract: We present a class of algorithms for state estimation in nonlinear, non-Gaussian state-space model…
12
Deep Learning for Dynamic Programming with Recursive Utility
用深度学习求解带递归效用的动态规划，93页长文含44图，金融与最优控制交叉前沿。
arXiv:2607.04278v1 Announce Type: cross Abstract: We propose the first deep learning algorithm, the Certainty Equivalent Learning (CEL) algorithm, for…
13
I Opened 3 Security Issues on Microsoft AutoGen and LlamaIndex. Here Is Why
AI Agent两大明星框架被曝441处递归执行漏洞，安全风险不容忽视。
I just opened 3 security issues on two of the most popular AI agent frameworks on GitHub (combined 110K+ stars). The Issues microsoft/autogen#7917 : D…
14
Multi-Head Recurrent Memory Agents
多智能体记忆新架构，多头设计提升长程推理与上下文保持能力。
arXiv:2607.01523v1 Announce Type: cross Abstract: Recurrent memory agents extend LLMs to arbitrarily long contexts by iteratively consolidating input …
15
Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing
多模态大模型在线编辑遇泛化难题？这项研究提出递归编辑新思路，让知识修正更精准稳定。
arXiv:2607.01978v1 Announce Type: new Abstract: Online multimodal knowledge editing requires injecting a continual stream of visual-textual correction…
16
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
长上下文推理新突破，递归证据回放让LLM精准捕捉关键信息
arXiv:2607.02509v1 Announce Type: new Abstract: Understanding and reasoning over long contexts has become a key requirement for deploying large langua…
17
When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs
代码大模型陷入自训练怪圈：这篇论文揭示了AI自我审查代码时可能发生的递归塌缩现象。
arXiv:2606.28438v1 Announce Type: cross Abstract: Recursive self-training can degrade neural generative models when generated data is reused without f…
18
Show HN: TinyAgents – a Rust based recursive LLM harness
Rust编写的递归LLM框架，解决上下文衰减问题，让有效上下文突破原始限制。
Hey Guys, I would like to showcase Tiny Agents, which is an entirely Rust-based RLM. RLMs are a recent and fantastic new innovation on how LLMs can be…
19
Recursive Joint Simulation in Games
提出递归联合模拟方法，为博弈中的多智能体决策提供新思路
arXiv:2402.08128v3 Announce Type: replace Abstract: Game-theoretic dynamics between AI agents could differ from traditional human-human interactions i…
20
How to Use a Trace Table to Solve Python Recursion Problems
用跟踪表可视化递归调用栈，轻松攻克Python递归难题，调试效率翻倍。
Recursion trips up more Python developers in technical interviews than almost any other concept. Not because recursion itself is complicated, but beca…