---
id: 20261018-T0-04
title: "自改进Agent会保留“错技能”：无Oracle算子归纳方法要求答案精确可验证"
title_en: "Self-Improving Agents Keep Wrong Skills; Oracle-Free Operator Induction Targets Exact Answers"
url: https://ai.daily.yangsir.net/daily/20261018-T0-04
issue_date: 2026-10-18
publish_date: 2026-10-17T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.20809
---

# 自改进Agent会保留“错技能”：无Oracle算子归纳方法要求答案精确可验证

论文指出自改进代理的一个实际问题：代理必须决定保留哪些新技能，而实践中它保留的是那些奖励高、能说服评审模型或能压缩技能库的技能，即使该技能本身是错的。在答案需要精确正确的场景下，这套筛选机制会失效。作者提出无Oracle的算子归纳方法，让代理自行生长出领域特定语言（DSL）来支持精确问答，而不是依赖外部评判或奖励信号来筛选技能。核心含义是：技能保留标准必须与答案的精确性对齐，否则自改进会稳定地积累错误。

## English Version

**Self-Improving Agents Keep Wrong Skills; Oracle-Free Operator Induction Targets Exact Answers**

The paper identifies a practical failure in self-improving agents: an agent must decide which new skills to keep, and in practice it keeps whatever earns high reward, convinces a judge model, or compresses its skill library, even when the skill is wrong. That breaks down when answers must be exactly right. The authors propose oracle-free operator induction, in which the agent grows its own domain-specific language (DSL) to support exact question answering rather than relying on external judges or reward signals to filter skills. The takeaway: skill retention criteria must align with answer exactness, or self-improvement will reliably accumulate errors.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.20809)

**详情页**：https://ai.daily.yangsir.net/daily/20261018-T0-04

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*