ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis

2026-09-26

AI Summary

This study addresses the limitation of existing methods that abstract experiences into fixed knowledge, which often leads to the loss of critical information. To this end, we propose ExpVoyager, a framework that reformulates skill synthesis as a dynamic navigation problem over raw experiences, enabling multi-perspective, fine-grained, on-demand access and tracking. The method introduces a Skill Curator mechanism that integrates multi-resolution view exploration with residual-need-guided navigation strategies to dynamically synthesize reusable skills. Experimental results demonstrate that ExpVoyager significantly enhances downstream task performance, with gains scaling continuously as experience volume increases. Furthermore, the proposed framework remains compatible with existing efficient skill systems.

Abstract

Learning from experience in LLM agents has become a key paradigm for developing self-evolving agents that continuously learn and expand their capabilities. Within this paradigm, synthesizing the agent skill has emerged as a promising solution for transforming accumulated experience into reusable procedural knowledge, serving as an important layer for the harness system that supplies agents at runtime. Despite its potential, existing approaches largely abstract past experience into fixed procedural knowledge before downstream demands are known, which risks discarding knowledge that later becomes critical while retaining instance-specific details irrelevant to future tasks. In this paper, we reframe agent skill synthesis as a dynamic navigation problem over past experience, where agents actively explore accumulated trajectories on demand for the current task with targeted and fine-grained access to experience knowledge. To this end, we propose ExpVoyager, a novel framework in which a skill curator navigates raw experience across different views and resolutions, continually identifying reusable procedural knowledge from what it observes while tracking remaining knowledge needs that guide where to navigate next. Extensive experiments demonstrate both the effectiveness and versatility of ExpVoyager, showing consistent improvements in downstream task performance, continual gains as the experience space scales, and practical compatibility with existing skills under efficient experience access.

Problem

• LLM agents
• skill synthesis
• experience learning
• procedural knowledge
• dynamic navigation

Innovation

• Experience Navigation
• Skill Synthesis
• LLM Agents
• Dynamic Exploration
• Procedural Knowledge