Skip to content

SkillCome: Group Contrast Skill Optimization with Dual Memory

Sep 2026 · 0 citations · 44 references
Computer Science

TL;DR

This work proposes SkillCome, a Skill-evolution method based on group Contrast optimization with dual memory that builds a systematic optimization process that transforms experience from observed successful trajectories into reusable skills.

Abstract

Skill evolution improves the capabilities of large language models by analyzing trajectories generated under a given skill and modifying the skill accordingly. Existing approaches typically generate a single trajectory per question. However, this provides insufficient optimization signals since it requires inferring effective skill edits from a solitary path. It is difficult to pinpoint which actions caused the failure in a failed trajectory, or to determine which actions in a successful one should be incorporated into the skill. Furthermore, they rely on a local batch of trajectories for analysis, making the optimization direction susceptible to noisy evidence. To address these, we propose SkillCome, a Skill-evolution method based on group Contrast optimization with dual memory. For each question, SkillCome generates trajectories and performs group contrast analysis to precisely identify key behavioral divergences between successful and failed trajectories, offering reliable optimization signals. The dual memory system further accumulates evidence from historical steps to track patterns shared across different groups, leading to more generalized optimization directions. Together, SkillCome builds a systematic optimization process that transforms experience from observed successful trajectories into reusable skills. Extensive experiments on six benchmarks spanning question answering, reasoning, and agentic tasks demonstrate the effectiveness of our method. SkillCome consistently outperforms baselines across five models of varying families and scales, with gains up to +5.69 points.

View source

Similar papers

SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting

SkillEvoReg, a general regularization framework for skill evolution inspired by anti-overfitting techniques in neural-network training, is introduced and suggested that explicit regularization is a useful complement to increasingly capable skill updaters.

Guan-Yu Nie, Fang-Zhou Zhu, Shi-Xiong Kai et al. · 3 citations
#artificial intelligence Preprint Sep 2026

SkillAdam: Stable and Efficient Skill Evolution for Agents

SkillAdam, an Adam-inspired framework for optimizing discrete and non-differentiable skill documents, is introduced, an Adam-inspired framework for optimizing discrete and non-differentiable skill documents with substantially fewer optimization iterations and lower cost than prior methods.

Gao-Yuan Li, Mei-Hao Fan, Yi-Zhe Liu et al. · 5 citations · ⚡3
Preprint Aug 2026

VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience

VCE-Skill is proposed, which distills noisy and implementation-specific public skill changes into reusable, structured version-change experience and adaptively fuses it with trajectory-derived proposals from the base evolver, thereby exploiting external experience while retaining task-specific evidence.

Jianming Chen, Xuanbin Ye, Yawen Wang et al. · 0 citations
#natural language process... Preprint Aug 2026

Write, Execute, Refine: From Skill Followers to Skill Optimizers via Reinforcement Learning from Execution Feedback

Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill. This gap suggests that following procedural guidance and improving it from execution evidence are distinct capabilities. Inference time loops can repair skills but do not improv...

Kang Peng, Zhi-Wei Zhang, Yichen Zhang et al. · 1 citation

SkillVine: Agent Skill Evolution via Branching Exploration

SkillVine is proposed, an automatic skill-evolution framework that formulates skill evolution as a graph search problem and employs a branching exploration strategy, and achieves a balance between exploration and exploitation.

Kai-Wei Liu, Ji-Qian Dong, Li-Ran Dong et al. · 0 citations
#artificial intelligence Preprint Sep 2026

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

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

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.