1
Before AI Ships Code, Show Me the Receipts
AI写代码前先看“收据”，五步打造自进化运维系统，实战干货满满
Article URL: https://www.pagerduty.com/eng/before-ai-ships-code-show-me-the-receipts/ Comments URL: https://news.ycombinator.com/item?id=48842378 Poin…
2
Closing the Loop: Formally Verified Law as a Reward Signal for Self-Improving Legal AI
把数学AI的“LLM提案、验证器把关”范式搬进法律领域，用形式化验证打造可验证的奖励信号，法律AI自改进的新路子。
arXiv:2606.23913v1 Announce Type: new Abstract: This article develops an architecture that creates a formally verifiable reward signal to train legal …
3
Show HN: Eidentic – TypeScript SDK for AI agents with self-improving memory
开源TypeScript SDK：AI agent自改进记忆、隔离执行与GDPR擦除，Apache-2.0许可。
Article URL: https://github.com/eidentic/eidentic Comments URL: https://news.ycombinator.com/item?id=48494704 Points: 4 # Comments: 0
4
AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library
解锁LLM新能力：自改进经验库让AI自动制定优化程序，无需人工干预的精妙方法。
arXiv:2510.18428v4 Announce Type: replace Abstract: Optimization modeling underlies critical decision-making across industries, yet remains difficult …
5
Show HN: Recursi – self-improving LLM-connected coding environment
自改进的编码环境，结合LLM智能交互，支持Web端免费使用，开源且无需注册。
A coding environment designed to be "recursively self improving".... but a whole lot more. Uses web based chatbots to save tons of money while being w…
6
A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula
从易到难课程驱动模型自我迭代，任务中心理论揭示高效训练新路径。
arXiv:2602.10014v3 Announce Type: replace Abstract: Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verif…
7
SIA: Self Improving AI with Harness & Weight Updates
提出SIA方法，让AI通过Harness与权重更新实现自我改进，打破人类调参瓶颈。
arXiv:2605.27276v1 Announce Type: new Abstract: Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them …
8
Understanding the Challenges in Iterative Generative Optimization with LLMs
揭示LLM迭代优化中的脆弱性：仅9%的智能体能成功自改进，挑战何在？
arXiv:2603.23994v2 Announce Type: replace-cross Abstract: Generative optimization uses large language models (LLMs) to iteratively improve artifacts (…
9
Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
用LLM代理自主设计基础模型架构，AIRA-Compose与AIRA-Design双框架实现递归自改进，跳出标准Transformer限制。
arXiv:2605.15871v1 Announce Type: new Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models …