Across four agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without retrieval-augmented skill initialization and updating.
Abstract
An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. Recent studies have explored the optimization of agent skills, contributing to a growing collection of publicly available skills spanning diverse tasks, domains, and harnesses. Despite millions of publicly shared skills, existing skill optimization methods largely overlook this accumulated knowledge, instead relying solely on expensive agent rollouts to iteratively refine skills for a target task. To address this, we propose \textbf{Retrieval-Augmented Skill Optimization (RASO)}, a framework that leverages an external skill corpus as prior knowledge throughout skill optimization. RASO retrieves relevant knowledge from existing skills and adapts it to the target task and harness via Cross-Harness Adaptation, accounting for mismatches in both domain and harness. RASO comprises two complementary stages: \textbf{Retrieval-Augmented Skill Initialization (RASI)} constructs a knowledge-grounded initial skill without requiring agent rollouts, while \textbf{Retrieval-Augmented Skill Update (RASU)} iteratively refines the skill by retrieving external knowledge guided by execution feedback. Across four agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without retrieval-augmented skill initialization and updating.
This work introduces PRACTICE, which trains a skill learner to discover and maintain a persistent skill library from past interaction trajectories while keeping the task executor frozen, and demonstrates that a compact skill learner delivers consistent performance improvements across successive library-update rounds fo...
Ziyi Bai, Si-Qi Li, Ting-Lei Huang et al.· 0 citations
SkillFM (Skill Flow Matching), a generative framework that synthesizes task-conditioned textual skills directly without test-time skill retrieval, is introduced, demonstrating that latent skill generation is an effective alternative to retrieval-based skill augmentation.
Zu-Ming Zhang, Jie He, Yi-Zhe Zhang et al.· arXiv.org· 0 citations
SkillAlign is proposed, a provider-agnostic framework that represents candidate skills as multi-view procedural cards and renders them through alternative exposure interfaces, including full instructions, hints, compressed summaries, workflows, or no exposure, which enables counterfactual evaluation where the task, age...
Shuo Ren, Xiaomian Kang, Jia-Jun Zhang· Proceedings of the 2026 Conf...· 1 citation
SkillSpec, a two-phase framework comprising consensus-gated evolution and representation specialization, is introduced, demonstrating that reliable skill evolution and representation specialization address complementary objectives: deciding what knowledge to retain and how to structure it for inference.
Huan-Cheng Chen, Xi Sun, Zhao-Qiong Huang et al.· 1 citation
COBRA-Skills is introduced, an efficient framework that formulates skill optimization as budgeted sequential optimization over a dynamically evolving candidate space and remains robust to changes in the agent harness and performs effectively when the target model itself is used for skill generation and refinement.
Ping-Chen Lu, Xiang-Yi Wang, Xiang Li et al.· 2 citations
UniSkill is introduced, which uses a shared policy to interact with the environment and propose skillbank edits (Add, Update, or No Edit) from the resulting trajectories and provides an actor-alignment signal by measuring how replacing the retrieved skill with a proposed skill changes the current actor's action log-lik...