1
翁荔新博客提出「自进化先从Harness开始」，DeepSeek崔添翼转发附议
翁荔提出自进化从Harness而非模型权重开始，元智能体优化Agent工作流设计，崔添翼转发支持
崔添翼：这个方向很容易出成果
2
Agentic Hardware Design as Repository-Level Code Evolution
HORIZON将硬件设计转化为仓库级代码进化，AI智能体框架实现硬件自进化，颠覆传统设计流程。
arXiv:2606.28279v1 Announce Type: cross Abstract: We present HORIZON, a self-evolving agent framework that treats hardware design as repository-level …
3
Self-Evolving Multi-Agent Systems via Textual Backpropagation
提出基于文本反向传播的多智能体自我进化框架，让智能体在协作中自动优化策略，无需人工干预。
arXiv:2506.09046v3 Announce Type: replace Abstract: Leveraging multiple Large Language Models (LLMs) has proven effective for addressing complex, high…
4
Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents
突破传统记忆局限：双过程认知记忆系统让LLM智能体实现自进化学习。
arXiv:2606.09483v1 Announce Type: new Abstract: Long-term memory for an LLM agent is more than retrieving the right passage at the right time. Current…
5
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
提出自进化编码代理Socratic-SWE，通过轨迹推导技能突破SWE任务训练瓶颈，为LLM代理能力提升开辟新路径。
arXiv:2606.07412v1 Announce Type: cross Abstract: LLM-driven software engineering agents have become a central testbed for real-world language-model c…
6
The Self-Evolving Agent: How to Build Closed-Loop AI Systems That Write and Optimize Their Own Code
让AI自动编写并优化自身代码的闭环系统实践指南，从提示工程到生产自适应性，破除“一次性完美”迷信。
We have all been there. You spend hours meticulously crafting the perfect system prompt or tool description for your AI agent. It performs beautifully…
7
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
LLM Agent技能自进化新方法：利用轨迹条件修正，解决冷启动下初始不完美技能改进难题。
arXiv:2606.01139v1 Announce Type: new Abstract: Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints,…
8
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
LLM智能体进化研究新视角：解耦外部框架更新与性能收益，揭示自进化能力的真正来源
arXiv:2605.30621v1 Announce Type: new Abstract: LLM agents are increasingly deployed as systems built around editable external harnesses, including pr…
9
SEAL: Synergistic Co-Evolution of Agents and Learning Environments
LLM代理自我进化新突破：协同策略与环境共同进化，解决代理-环境错配难题
arXiv:2605.24426v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evoluti…
10
11
One-Way Policy Optimization for Self-Evolving LLMs
提出单向策略优化方法，让大模型在无外反馈下自我进化，提升推理与对齐能力。
arXiv:2605.22156v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling re…
12
EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
时间中心自进化框架，让视频大语言模型深度感知时序动态，性能飞跃
arXiv:2605.21931v1 Announce Type: new Abstract: Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoni…
13
Show HN: Autodidact – Self-evolving local-first AI agent
本地优先AI代理自动处理Ollama依赖，安装模型启动一气呵成，适合不想折腾环境的开发者。
pip install autodidact && autodidact init Comments URL: https://news.ycombinator.com/item?id=48194739 Points: 4 # Comments: 0
14
D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
提出双难度感知自进化方法，解决强化学习训练数据稀缺与动态难度转移的挑战。
arXiv:2605.17037v1 Announce Type: new Abstract: Reinforcement learning (RL) has demonstrated potential for enhancing reasoning in large language model…
15
TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in Microservices
拓扑感知多智能体框架自进化解决微服务根因分析，应对噪声、级联故障和拓扑漂移三大挑战
arXiv:2605.15611v1 Announce Type: new Abstract: Root cause analysis (RCA) in microservices is challenging due to (i) noisy and heterogeneous multimoda…
16
AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
提出动态自进化安全评估框架，解决大模型静态基准无法应对AI风险演变的问题。
arXiv:2509.26100v2 Announce Type: replace Abstract: The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliab…