SkillGen: Learning Domain Skills for In-Context Sequential Decision Making

TL;DR

SkillGen introduces a skill-based in-context learning framework that constructs domain-specific prompts from trajectory graphs, improving decision-making efficiency in large language models across multiple environments.

Contribution

It presents a novel method for generating fine-grained, context-aware prompts by leveraging domain-level graphs and high-utility actions, enhancing ICL effectiveness.

Findings

Achieves 5.9%-16.5% improvement in progress rate across models.

Demonstrates effectiveness on ALFWorld, BabyAI, and ScienceWorld environments.

Provides theoretical analysis linking high-utility segments to task identifiability.

Abstract

Large language models (LLMs) are increasingly applied to sequential decision-making through in-context learning (ICL), yet their effectiveness is highly sensitive to prompt quality. Effective prompts should meet three principles: focus on decision-critical information, provide step-level granularity, and minimize reliance on expert annotations through label efficiency. However, existing ICL methods often fail to satisfy all three criteria simultaneously. Motivated by these challenges, we introduce SkillGen, a skill-based ICL framework for structured sequential reasoning. It constructs an action-centric, domain-level graph from sampled trajectories, identifies high-utility actions via temporal-difference credit assignment, and retrieves step-wise skills to generate fine-grained, context-aware prompts. We further present a theoretical analysis showing that focusing on high-utility segments supports task identifiability and informs more effective ICL prompt design. Experiments on ALFWorld, BabyAI, and ScienceWorld, using both open-source and proprietary LLMs, show that SkillGen achieves consistent gains, improving progress rate by 5.9%-16.5% on average across models.