Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning

Hugging Face Daily Papers Papers
reinforcement-learning agentic-ai skill-management framework llm-agents

Summary

The article introduces the SLIM framework, which optimizes dynamic skill lifecycles in agentic reinforcement learning by jointly updating active skill sets with policy learning. Experiments show SLIM outperforms baselines by improving task performance through efficient skill retention and expansion.

Large language model agents increasingly rely on external skills to solve complex tasks, where skills act as modular units that extend their capabilities beyond what parametric memory alone supports. Existing methods assume external skills either accumulate as persistent guidance or internalized into the policy, eventually leading to zero-skill inference. We argue this assumption is overly restrictive, since with limited parametric capacity and uneven marginal contribution across skills, the optimal active skill set is non-monotonic, task- and stage-dependent. In this work, we propose SLIM, a framework of dynamic Skill LIfecycle Management for agentic reinforcement learning (RL), which treats the active external skill set as a dynamic optimization variable jointly updated with policy learning. Specifically, SLIM estimates each active skill's marginal external contribution through leave-one-skill-out validation, then applies three lifecycle operations: retaining high-value skills, retiring skills whose contribution becomes negligible after sufficient exposure, and expanding the skill bank when persistent failures reveal missing capability coverage. Experiments show that SLIM outperforms the best baselines by an average of 7.1% points across ALFWorld and SearchQA. Results further indicate that policy learning and external skill retention are not mutually exclusive: some skills are absorbed into the policy, while others continue to provide external value, supporting SLIM as a more general paradigm for skill-based agentic RL.
Original Article
View Cached Full Text

Cached at: 05/12/26, 07:30 AM

Paper page - Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning

Source: https://huggingface.co/papers/2605.10923

Abstract

SLIM framework manages dynamic skill lifecycles in agentic reinforcement learning by optimizing active skill sets jointly with policy learning, outperforming existing methods in complex task environments.

Large language model agents increasingly rely onexternal skillsto solve complex tasks, where skills act as modular units that extend their capabilities beyond what parametric memory alone supports. Existing methods assumeexternal skillseither accumulate as persistent guidance or internalized into the policy, eventually leading to zero-skill inference. We argue this assumption is overly restrictive, since with limited parametric capacity and uneven marginal contribution across skills, the optimal active skill set is non-monotonic, task- and stage-dependent. In this work, we propose SLIM, a framework of dynamicSkill LIfecycle Managementforagentic reinforcement learning(RL), which treats the active external skill set as adynamic optimization variablejointly updated withpolicy learning. Specifically, SLIM estimates each active skill’smarginal external contributionthroughleave-one-skill-out validation, then applies three lifecycle operations: retaining high-value skills, retiring skills whose contribution becomes negligible after sufficient exposure, and expanding the skill bank when persistent failures reveal missing capability coverage. Experiments show that SLIM outperforms the best baselines by an average of 7.1% points across ALFWorld and SearchQA. Results further indicate thatpolicy learningand externalskill retentionare not mutually exclusive: some skills are absorbed into the policy, while others continue to provide external value, supporting SLIM as a more general paradigm for skill-based agentic RL.

View arXiv pageView PDFGitHub2Add to collection

Get this paper in your agent:

hf papers read 2605\.10923

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.10923 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.10923 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.10923 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Progressive Agent Skill Generation via Reinforcement Learning

Hugging Face Daily Papers

Introduces Skill-α, a reinforcement learning method for progressively generating high-quality agent skills by treating skill generation as sequential editing with a rollback reward. It improves downstream success rates over existing baselines on CL-Bench and tau2-bench.

SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration

arXiv cs.AI

SkillFlow proposes a flow-driven recursive skill evolution framework for LLM-based agentic orchestration, using Tempered Trajectory Balance to prevent strategy collapse and provide transparent credit assignment. Experiments on 14 datasets show significant improvements over baselines in QA, math, code, and decision-making tasks.