English(EN) SkillDuet: Co-Evolving Models and Skills through Response Feedback

SkillDuet框架共同演进大型语言模型和技能，以增强强化学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-14 05:00

研究人员开发了SkillDuet，一个旨在通过共同演进大型语言模型（LLMs）及其相关技能来增强强化学习的框架。该系统将参数更新与可重用文本技能的演进相结合，使技能能够指导模型交互和后续更新。SkillDuet表现强劲，在使用Qwen3-4B模型时，在ALFWorld上成功率达到98.57%，在WebShop上成功率达到92.97%，优于SEED-API基线。该框架的有效性依赖于基于响应的技能选择和整合到持久的全局技能集中，突显了技能内容和模型兼容性对于递归自我改进的重要性。 AI

影响通过技能共同演进，为大型语言模型的递归自我改进引入了一种新颖的方法。

排序理由该集群包含一篇详细介绍LLM强化学习新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM强化学习新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Xingguang Ji, Ziqiang Dong, Yubo Zhang, Xi Leng, Ninghua Yan, Yang Yang, Guanjun Jiang · 2026-11-14 05:00

SkillDuet：通过响应反馈共同演进模型和技能

arXiv:2611.12109v2 Announce Type: replace Abstract: During reinforcement learning, experience can be both internalized in LLM parameters and retained externally as reusable textual skills. Parameter updates alter the model's behavior and the interaction experience from which new …

本文如何被排名

报道来源 [1]

SkillDuet：通过响应反馈共同演进模型和技能

相关实体

相关话题