paper-with-me

홈 › Papers

Can Language Models Compose Skills In-Context?

2025-10-27 · Zidong Liu, Zhuoyan Xu, Zhenmei Shi, Yingyu Liang arxiv

Composing basic skills from simple tasks to accomplish composite tasks is crucial for modern intelligent systems. We investigate the in-context composition ability of language models to perform composite tasks that combine basic skills demonstrated in in-context examples. This is more challenging than the standard setting, where skills and their composition can be learned in training. We conduct systematic experiments on various representative open-source language models, utilizing linguistic and logical tasks designed to probe composition abilities. The results reveal that simple task examples can have a surprising negative impact on the performance, because the models generally struggle to recognize and assemble the skills correctly, even with Chain-of-Thought examples. Theoretical analysis further shows that it is crucial to align examples with the corresponding steps in the composition. This inspires a method for the probing tasks, whose improved performance provides positive support for our insights.

📄 PDF Abstract BibTeX arXiv:2510.22993

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Skill Neologisms: Towards Skill-based Continual Learning

2026-05-06 · Antonin Berthon, Nicolas Astorga, Mihaela van der Schaar arxiv

Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable manner is an open problem: fine-tuning and…

Continual Learning

More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries

2026-05-21 · Hongwen Song, Song Wei arxiv

Skill libraries allow LLM agents to load task-specific instructions on demand, letting non-expert users solve domain-specific tasks through natural language without knowing which skills exist or how they work. However, p…

A Decomposition Perspective to Long-context Reasoning for LLMs

2026-04-09 · Yanling Xiao, Huaibing Xie, Guoliang Zhao, Shihan Dou 외 arxiv

Long-context reasoning is essential for complex real-world applications, yet remains a significant challenge for Large Language Models (LLMs). Despite the rapid evolution in long-context reasoning, current research often…

Reinforcement Learning

Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose

2026-06-16 · Xueping Gao arxiv

LLM agents increasingly rely on external skills -- reusable tool specifications -- but real-world tasks often require composing multiple skills, not just selecting one. We formalize this as the Compositional Skill Routin…

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

2026-06-04 · Aofan Yu, Chenyu Zhou, Tianyi Xu, Zihan Guo 외 arxiv

Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and exposes skill content as plaintext. We pr…