---
title: "SkillRise：跨任务技能进化的智能体强化学习框架"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.26784v1"
permalink: "https://feed.astralor.com/items/itm_a29e20673f899c7ce8272af1"
published: "2026-07-29T11:26:33.000Z"
score: 81
channel: "ai"
tags: ["ALFWorld","ScienceWorld","SkillRise","WebShop","多任务技能迁移","智能体强化学习"]
---

# SkillRise：跨任务技能进化的智能体强化学习框架

## AI 点评

> 这篇论文解决了一个很实际的问题：如何让智能体在多个相关任务间复用技能，而不是每个任务都从零学起。SkillRise的「渐进式序列+单策略交替」设计既简洁又有效，实验中的Pass@1提升和测试时扩展性都很有说服力。对于正在构建多任务Agent团队或研究技能迁移的读者来说，非常值得一读。

## 速览

SkillRise是一个统一的强化学习框架，旨在让大语言模型智能体在相关但不同的任务之间学习可复用的技能。该框架将任务实例组织成渐进式序列，利用单一策略交替进行任务求解和技能文档的持续优化。实验表明，在ALFWorld、WebShop和ScienceWorld三个基准上，SkillRise的Pass@1性能超越最强基线2.3至8.5个百分点；它还展现出跨任务的测试时扩展能力，并在保持强劲性能的同时显著降低多阶段技能学习管线的运行时开销。

## 关键点

- SkillRise将多个相关任务组织为渐进式序列，通过单一策略同时进行任务求解与技能文档策展。
- 解耦的跨任务信用分配机制：当前任务结果监督求解，折现的未来结果监督技能策展。
- 在ALFWorld、WebShop和ScienceWorld上，Pass@1超过现有方法，提升2.3–8.5个百分点。
- 测试时随着相关任务序列增长性能持续提升，表明技能跨任务迁移而非同一任务重复采样。

## 全文

Large language model agents often encounter related yet distinct tasks that share reusable solution patterns. Yet standard agentic reinforcement learning treats tasks as independent episodes, while existing approaches to skill learning either focus on repeated attempts of one task or use pipelines with multiple stages that entangle extraction, retrieval, and execution. We introduce SkillRise, a unified reinforcement learning framework for learning skills across tasks. SkillRise organizes related instances into progressively challenging sequences and uses a single policy to alternate between task solving and curating an evolving skill document passed directly to the next task. Decoupled credit assignment across tasks supervises solving with the current task outcome and curation with discounted downstream outcomes. Experiments on ALFWorld, WebShop, and ScienceWorld show that SkillRise achieves the strongest Pass@1 performance among the compared methods, with gains over the strongest baseline ranging from 2.3 to 8.5 percentage points. Although trained across distinct tasks, its learned curation policy remains effective for repeated attempts on the same task. Further analysis reveals scaling at test time across tasks: performance improves with longer sequences of related tasks even when each task is attempted only once. This trend suggests that SkillRise reuses transferable skills across tasks rather than benefiting from repeated sampling of the same task. SkillRise further retains strong performance while substantially reducing the runtime overhead of skill learning pipelines with multiple stages. Together, these results provide a simple and efficient training paradigm for LLM agents to extract, refine, and reuse transferable skills across tasks.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_a29e20673f899c7ce8272af1