智能体
arxiv.org ·
COBRA-Skills：面向智能体技能优化的上下文赌博机引导进化
该论文提出 COBRA-Skills，把 LLM 智能体的可复用技能优化表述为动态演化候选空间上的预算化序列优化问题，用上下文赌博机引导评估资源的分配，并基于执行反馈持续进化技能种群。作者称在 6 个异构智能体基准和 3 个目标模型上平均表现优于对比方法，优化成本比 SkillOpt 降低 55–58%，每个基准仅需 50 个唯一优化样本，且对 agent harness 变化保持稳健。上述结论来自论文摘要，尚待独立验证。
AI推荐理由 arXiv 新论文（2026-09-10 提交），提出 COBRA-Skills 框架，将智能体技能优化建模为动态候选空间上的预算化序列优化，结合上下文赌博机引导的优先级排序与基于执行反馈的技能进化。摘要给出可核验的具体结果：在 6 个异构智能体基准、3 个目标模型上取得对比方法中最强平均表现，优化成本较 SkillOpt 降低 55–58%，每个基准仅用 50 个唯一优化样本，并报告对 agent harness 变化保持稳健。局限在于结果均来自作者自述摘要，尚无第三方复现或代码可用性证据，且未给出绝对性能数值。
78
正文
Computer Science > Artificial Intelligence
arXiv:2609.11682 (cs)
[Submitted on 10 Sep 2026]
Title:COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
Authors:Pingchen Lu, Xiangyi Wang, Xiang Li, Jie Mao, Zikun Qu, Junfeng Luo, Yao Shu, Bryan Kian Hsiang Low, Zhongxiang Dai
View a PDF of the paper titled COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization, by Pingchen Lu and 8 other authors
View PDF
HTML (experimental)
Abstract:Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience, yet existing skill optimization methods often rely on costly execution-based evaluation and substantial task data. We introduce \textbf{COBRA-Skills}, an efficient framework that formulates skill optimization as budgeted sequential optimization over a dynamically evolving candidate space. COBRA-Skills couples contextual-bandit-guided prioritization with evidence-grounded skill evolution, selectively allocating evaluations to promising or informative candidates while continually refining the skill population from execution feedback. Across six heterogeneous agent benchmarks and three target models, COBRA-Skills consistently achieves the strongest average performance among compared methods, while reducing optimization cost by 55--58\% relative to SkillOpt and using only 50 unique optimization examples per benchmark. Further analyses show that COBRA-Skills remains robust to changes in the agent harness and performs effectively when the target model itself is used for skill generation and refinement.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.11682 [cs.AI]
(or
arXiv:2609.11682v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.11682
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Pingchen Lu [view email]
[v1]
Thu, 10 Sep 2026 15:12:24 UTC (503 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization, by Pingchen Lu and 8 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)