SOURCE-LINKED INTELLIGENCE

Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Large language model agents increasingly rely on execution traces to master complex interactive tasks. However, current paradigms are bottlenecked by shallow trajectory retrieval and flat skill summarization, fundamentally ignoring the temporal dependencies and outcome-conditioned topology of agent behavior. We introduce Trace2Tower, a transition-aware EigenTrace framework that distills raw trajectories into a robust skill hierarchy. Trace2Tower abstracts step-level interactions into canonical events, constructing a unified graph governed by semantic compatibility, transition dynamics, and out

Read original source ↗ Open in workspace

recordType

paper

region

Global