跳到正文
arXiv cs.AI· Haihan Zhang, Wendao Wu, Chenheng Zhang, Chunyuan Zheng, Yanyi Li, Cong Fang, Haoxuan Li, Zhouchen Lin·· 23 小时前AI 评分45

Colombo:面向 Oracle 优化的前沿到前沿自动研究系统

Colombo: A Frontier-to-Frontier Autoresearch System for Oracle-Based Optimization

AI 导读

Colombo 是一个自组织 AI 研究者系统,首次落地于 Oracle 优化,通过 Complexity Atlas 记录可实现保证与不可避免极限之间的前沿差距。

正文 · 原文

View PDF HTML (experimental)

Abstract:Science advances from frontier to frontier as discoveries reshape what is known and create the basis for further discovery. We present Colombo, a self-organizing AI researcher that drives this renewal, first instantiated in oracle-based optimization. Here, the central question is how efficiently a problem class can be solved through a prescribed information interface and what costs no admissible algorithm can avoid. The gap between achievable guarantees and unavoidable limits defines the frontier recorded in its Complexity Atlas, a living map of frontier settings and the current state of knowledge. Self-Organization turns unresolved gaps into adaptive research programmes, coordinating conjecture formation, mathematical investigation, and replanning as evidence accumulates. Adversarial Co-Ascent develops algorithms and hard families through reciprocal challenge, exposing mechanisms of information use and concealment that guide stronger methods and proofs of unavoidable costs. Independent review and Lean-based formal certification check mathematical claims, while the Long-Term Memory carries supported findings and research experience across settings. To date, Colombo has established optimal or near-optimal rates for more than fifty settings in the Atlas. Colombo thus takes a concrete step toward Autopoietic Science: a scientific process whose validated advances regenerate the conditions of its own progress, continually reshaping how inquiry is organized and what it can discover.
Subjects: Artificial Intelligence (cs.AI); Optimization and Control (math.OC)
Cite as: arXiv:2611.23080 [cs.AI]
  (or arXiv:2611.23080v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23080

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Wendao Wu [view email]
[v1] Tue, 17 Nov 2026 17:06:23 UTC (7,249 KB)

来源:arXiv cs.AI · arxiv.org