arXiv：cs.LG· Seung Won Wilson Yoo, Chang Zeng, Aditi Somayajula, Sahithi Ankireddy, Rohan Kosalge, Avishree Khare, John Mitchell, Aditya G. Parameswaran, Rajhans Samdani, Anupam Datta·· 11 小时前
CoCoEvolve：用元反思进化优化生产级 AI 系统
Meta-Reflective Evolution Effectively Improves Production AI Systems
AI 导读
研究团队提出进化优化器 CoCoEvolve（Cortex Code Evolve），基于"元反思"机制让智能体变异器从完整进化历史中检索证据并探测在线系统后再提出变异。
正文
Abstract:Large Language Model (LLM)-guided evolutionary optimization has successfully improved prompts, programs, and even entire AI systems. Most optimization methods select a candidate from the search frontier, then mutate it in one LLM pass based only on its failures. This focus on the frontier can stall on production AI systems, where isolated failures reveal little about complex, hidden interactions. We introduce CoCoEvolve (Cortex Code Evolve), an evolutionary optimizer built around what we call meta-reflection, wherein an agentic mutator (Cortex Code) selectively retrieves evidence from the entire evolutionary history and probes the live system before verifying and proposing mutations. We apply CoCoEvolve to optimize three classes of production AI systems: data agents, LLM-powered data pipelines, and data engineering workflows. On DABStep, CoCoEvolve tops the public leaderboard, reaching 92.8% held-out hard accuracy compared to 78.4% for Meta-Harness and 30.4% for GEPA under matched conditions. Across six LLM data pipeline workloads, it outperforms every evaluated baseline. On data-eng-bench, CoCoEvolve lifts test-set solve rate from 59.1% to 77.4%, past the best baseline of 73.6%. It also has 11 percentage points higher accuracy than GEPA on HotpotQA while remaining competitive with specialized optimizers on established mathematical and systems benchmarks. Matched ablations confirm that each component of CoCoEvolve contributes to these gains, demonstrating the value of meta-reflection for optimizing production AI systems.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.12794 [cs.LG] |
| (or arXiv:2610.12794v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12794 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Seung Won Wilson Yoo [view email]
[v1]
Thu, 8 Oct 2026 23:00:44 UTC (460 KB)
来源：arXiv：cs.LG · arxiv.org