SkillCome improves large language model skills with group contrast learning
SkillCome: Group Contrast Skill Optimization with Dual Memory
Artificial Intelligence
Summary
Large language models learn better by practicing skills and improving from their experience. Past methods only used one example of how a model solved a problem, making it hard to understand what worked or failed. The researchers developed SkillCome, which looks at groups of successful and failed attempts together to find important differences and improve learning. SkillCome also remembers past experiences to guide better learning overall. Tests showed it helps models do better at answering questions and reasoning.
What this means in practice
- •For ai development teams: Enhance large language model training by using SkillCome’s group contrast method to improve skill optimization and overall task performance.
- •For customer support automation teams: Use improved skill learning to build more effective AI agents that handle reasoning and question-answering tasks with fewer errors.
Authors
Haolin Li, Feng Hong, Ang Li, Chilin Fu, Weichang Wu, Ya Zhang, Yanfeng Wang, Xiaolu Zhang, Jiangchao Yao
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.