PulseAugur
中
实时 20:04:01
English(EN) R$^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution

AI代理通过演化的外部模型探索递归自我改进 · 跟踪10个来源

多篇研究论文探讨了AI代理的递归自我改进(RSI)技术,旨在无需持续的人工干预或核心模型的再训练即可增强其能力。这些方法侧重于演化外部组件,如验证器、约束器或世界模型,然后由这些组件指导代理的学习和决策过程。方法包括用于验证器程序的统一协同演化(UCoE)、用于具身代理的AdaRSI、用于策略和记忆适应的MMLA-RSI,以及用于显式世界-语言-动作模型的D-World。其他研究引入了物理RSI(用于机器人)、AReaL-RSI(用于协调研究团队)和利用预测世界模型的RSI-Anything等框架,所有这些都为更自主和有效的AI开发做出了贡献。 AI

影响 这些多样化的递归自我改进方法可以加速AI的自主性,并减少对模型开发中人工监督的依赖。

排序理由 arXiv上发表了多篇研究论文,详细介绍了AI中递归自我改进的新方法和框架。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 27 个来源。 我们如何撰写摘要 →

AI代理通过演化的外部模型探索递归自我改进 · 跟踪10个来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
arXiv上发表了多篇研究论文,详细介绍了AI中递归自我改进的新方法和框架。
Source corroboration
27 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
50 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+7 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [27]

  1. arXiv cs.AI TIER_1 English(EN) · Yewei Zhao, Derong Xu, Wei Chen, Yin Xu, Peilun Zhou, Xiaohan Wang, Guojun Yin, Wei Lin, Mingjun Xiao ·

    从轨迹到差异化技能:面向自改进智能体的认知差异化

    arXiv:2610.23599v1 Announce Type: new Abstract: Large language model (LLM) agents tackle complex tasks through reasoning and interaction with external environments. Agent skills provide persistent, transferable capabilities that guide task planning, inform contextual decisions, s…

  2. arXiv cs.AI TIER_1 English(EN) · Yaolun Zhang, Tianyi Xu, Yujie Zhao, Jishen Zhao, Qingyun Wu, Huazheng Wang ·

    EvalResearchBench:AI代理能否构建自身的反馈以实现递归自我改进?

    arXiv:2610.04184v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts reduce this cost by selecting b…

  3. arXiv cs.AI TIER_1 English(EN) · Mingda Zhang, Qiang Huang, Yanjin Li, Zijia Wang, Qika Lin, Xiaoying Tang, Tiesunlong Shen ·

    R$^2$ Flow:通过递归技能演化实现递归自我改进

    arXiv:2609.33867v2 Announce Type: replace Abstract: LLM-based agents can improve themselves across tasks by reusing and revising the skills they orchestrate into executable procedures. Flow-based training fits this loop: it samples procedures in proportion to reward, and the flow…

  4. arXiv cs.AI TIER_1 English(EN) · Renhao Li, Xinjie Shen, Yang Su, Jianhong Tu, Derek F. Wong, Dayiheng Liu, Min Yang ·

    MetaExp:通过可验证的跨任务环境扩展,在经验中学习自我改进

    arXiv:2610.21492v1 Announce Type: new Abstract: Language-model agents can accumulate interaction feedback, but reliably turning that feedback into reusable experience remains challenging. Existing methods either optimize external experience scaffolds or train experience-related b…

  5. arXiv cs.CL TIER_1 English(EN) · NeoHorse Team, Guoliang Cao, Guohao Dai, Tianyu Guo, Kai Han, Hailin Hu, Zihan Jiang, Xiang Kuang, Boxun Li, Yulong Li, Zehua Pei, Yuchuan Tian, Jiamin Wang, Yu Wang, Yunhe Wang, Yihong Wu, Haiyang Xu, Shuo Zhang, Hang Zhou, Siyang Cheng, Jiayu Fan, Wei … ·

    NeoHorse-1:通过带路由的代理训练实现递归自我改进

    arXiv:2609.08183v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We present NeoHorse-1, a family of agent-native mode…

  6. arXiv cs.AI TIER_1 English(EN) · Huan Zhang, Mingju Chen, Dongxu Zhou, Can Lv, Sen Cui, Faguo Wu, Shiji Zhou ·

    RSIFlow:具有不断演进的元代理的自适应自我改进工作流

    arXiv:2610.21791v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capabilities in complex tasks, including code generation, tool use, and multi-hop question answering. Existing self-improvement methods enhance agent performance through mod…

  7. arXiv cs.AI TIER_1 English(EN) · Brian B. Moser, Stanislav Frolov, Tobias C. Nauen, Federico Raue, Andreas Dengel ·

    自我提升问题

    arXiv:2610.21646v1 Announce Type: new Abstract: With the rise of large language models, agentic systems are becoming increasingly autonomous, as they write code, call tools, revise prompts, and propose modifications to their own components. This autonomy raises a fundamental ques…

  8. arXiv cs.AI TIER_1 English(EN) · Leijun Zhou, Yanke Yu, Zhihao Liu, Qu Xiang, Tiancheng Hu, Yiru Dong, Yihan Wu, Yangxi Xiang, Xuejun Wu, Xi Chen, Buyue Qian, Yaowei Zheng, Junhao Hu ·

    从现有方法到新研究思路:递归自我改进的两种视角

    arXiv:2610.14625v1 Announce Type: new Abstract: Recursive self-improvement (RSI) offers a route to AI systems that participate in their own continued development. Recent methods allow language agents to retain changes to their parameters, memory, skills, and code for subsequent e…

  9. arXiv cs.AI TIER_1 English(EN) · Tianyi Xu, Yaolun Zhang, Yiran Wu, Joe Nguyen, Shengyu Dai, Saba Moeinizade, Zhenwen Shao, Qingyun Wu, Huazheng Wang ·

    面向开放式任务的无训练自改进的验证器-约束器协同进化

    arXiv:2610.17609v1 Announce Type: new Abstract: Training-free self-improvement lets an agent use feedback to revise the response it is about to return and to update the harness state that shapes how it handles later tasks. On open-ended tasks that feedback rarely comes from refer…

  10. arXiv cs.AI TIER_1 English(EN) · Wenhao Zhou, Jiajun Song, Haitao Wang, Zipeng Qiu, Yingqi Peng, Ruida Xu, Jiale Li, Wenshuang Li, Shusheng Xu, Wei Dong, Hao Dai, Tongkai Yang, Yi Gao, Binhang Yuan ·

    AReaL-RSI:递归自改进的自适应缩放与协调

    arXiv:2610.18083v1 Announce Type: new Abstract: Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, more researcher agents can explore more hypotheses, but early evaluation scores m…

  11. arXiv cs.AI TIER_1 English(EN) · Hai Zhou, Fan Yang, Zeyi Chen, Lejun Zhang, Chenyang Fu, Jianping Li, Jiayi Zhu, Xianyang Liu, Yingxuan Yang, Lili Meng, Lu Wang, Xinyang Han, Jiankai Sun, Weirui Ye, Guanchu Wang, Wanhua Li, Ming Zhou, Boyi Li, Ming Jin, Kun Shao, Muhao Chen, Guang Chen… ·

    谁在改进机器人?迈向物理递归自改进

    arXiv:2610.18842v1 Announce Type: new Abstract: Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Self-Improvement (Physical RSI), in which physical experience guides lasting update…

  12. arXiv cs.AI TIER_1 English(EN) · Xuan Wen, Baichao Wang ·

    D-World:一种具有递归自改进和双重控制的显式世界-语言-动作模型

    arXiv:2610.17114v1 Announce Type: cross Abstract: Frontier large language models (LLMs) now reason about space well enough to program robots, yet the world models behind robot policies are implicit, held in network weights or predicted video, and cannot be inspected or corrected …

  13. arXiv cs.CL TIER_1 English(EN) · Junyi Zou, Avrova Donz ·

    MMLA-RSI:通过RTT和RTMA实现递归自我改进

    arXiv:2610.20294v1 Announce Type: new Abstract: An agent can improve its behavior within an unresolved problem by changing how it acts and which experience it retains. We propose MMLA-RSI, a recursive self-improvement scheme with two implementations in Memory-Mediated Learning Ar…

  14. arXiv cs.CL TIER_1 English(EN) · Peidong Wang, Ying Chang, Zhiming Ma, Xiaocui Yang, Shi Feng, Daqi Liu, Yuzhe Yang, Xu Cao, Chuang Wang, Jian Su, Daling Wang ·

    AdaRSI:具身智能体的按需递归自改进

    arXiv:2610.20474v1 Announce Type: new Abstract: Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy, but embodied RSI methods either refine the harness around a frozen executor and s…

  15. arXiv cs.CL TIER_1 English(EN) · Taoyong Cui, Pinxian Zeng, Wanghan Xu, Hao Xiao, Shuhan Xue, Qiang Gao, Wanli Ouyang, Pheng Ann Heng, Zhenfei Yin, Yingcheng Wu, Ling Yang ·

    RSI-Anything:利用世界模型解锁递归自我改进

    arXiv:2610.13912v1 Announce Type: new Abstract: Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything,…

  16. arXiv cs.AI TIER_1 English(EN) · Hyunin Lee, Jinglue Xu, Jeffrey Seely, Donghyun Lee, Somayeh Sojoudi, Matei Zaharia, Yujin Tang ·

    通过多智能体自监督实现递归自我改进

    arXiv:2610.12176v1 Announce Type: new Abstract: Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed what even human experts can reliably assess, leaving the model itself (optimize…

  17. arXiv cs.AI TIER_1 English(EN) · Haoyu Zhao, Zhengxu Yu, Zhiyuan He, Meng Fang, Rasul Tutunov, Haitham Bou-Ammar, Weilin Luo, Jun Wang ·

    Memento 3: 基于模型的递归自我改进与反思性规则手册

    arXiv:2610.11794v1 Announce Type: new Abstract: Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as new evidence arrives. Yet limited observations can support multiple world models that explain past interactions…

  18. Hugging Face Daily Papers TIER_1 English(EN) ·

    RSI-Anything:利用世界模型解锁递归自我改进

    Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything, a domain-general framework built on JEPA-Anythi…

  19. arXiv cs.LG TIER_1 English(EN) · Fanqing Meng, Lingxiao Du, Haocheng Lu, Qiguang Chen, Ziqi Zhao, Zijian Wu, Jiayuan Zhuo, Mengkang Hu, Michael Qizhe Shieh ·

    RSIGym:递归式自我改进的灵活环境

    arXiv:2610.10310v1 Announce Type: new Abstract: Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying agent-proposed changes also requires substantial research infrastructure. Existing settings often leave agents to rebuild ro…

  20. Hugging Face Daily Papers TIER_1 English(EN) ·

    Memento 3: 基于模型的递归自我改进与反思性规则手册

    Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as new evidence arrives. Yet limited observations can support multiple world models that explain past interactions but predict different outcomes in unseen states…

  21. arXiv cs.AI TIER_1 English(EN) · Jinfeng Xu, Zheyu Chen, Ziyue Peng, Zheng Lin, Wenhao Yuan, Jian Chen, Shujie Li, Edith Ngai ·

    超越成功率准确性:推荐系统中递归自改进的状态保持

    arXiv:2610.07105v1 Announce Type: cross Abstract: Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the successor consolidates the update, although pre- and po…

  22. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Edith Ngai ·

    超越成功率准确性:推荐系统中递归自改进的状态保持

    Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the successor consolidates the update, although pre- and post-update models may retain complementary ranking …

  23. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Rohan Ramanath ·

    从有效到有用:递归自改进推荐的后验证获取

    Sequential recommenders can generate synthetic interaction sequences and retrain on the augmented corpus in a recursive self-improvement loop. To limit error accumulation, current methods verify each generated sequence remains predictive of the user's real interactions and discar…

  24. Hacker News — AI stories ≥50 points TIER_1 English(EN) · hardmaru ·

    通过集体智能实现递归式自我改进

  25. Bluesky Jetstream — AI desk TIER_1 English(EN) · hardmaru.bsky.social ·

    Sakana AI 新论文:通过多智能体自监督(MASS)实现递归自我改进。

    New Sakana AI paper: Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS). Blog: pub.sakana.ai/mass/ Paper: arxiv.org/abs/2610.12176 How do we keep improving AI when tasks become too complex for humans to reliably evaluate? The model eventually hits a supervi…

  26. dev.to — LLM tag TIER_1 English(EN) · GINIGEN AI ·

    一个自学成才的模型,十一个第一的头衔:这需要什么

    <h2> TL;DR </h2> <p>One self-improving model family now holds eleven public number-one benchmark records at the same time, across math, science, law, structured output, and decisions. The interesting part is not any single score, it is that a recursive self-improvement loop, boun…

  27. Mastodon — mastodon.social TIER_1 English(EN) · CuratedHackerNews ·

    通过集体智能实现递归式自我改进 https:// pub.sakana.ai/mass/ # ai

    Recursive self-improvement through collective intelligence https:// pub.sakana.ai/mass/ # ai