כתבה
arXiv cs.LG ·
VERSE: אופטימיזציה עצמית מאומתת להרשם סלפ-אבולוציה
VERSE: Verified Self-Evolving Optimizer for Agent Harnesses
אופטימיזציה עצמית של האופטימיזציה משפרת את ביצועי הרשם עם וריפיקציה באמצעות תפעול.
תקציר מקורי באנגליתarXiv:2610.02616v1 Announce Type: cross Abstract: Harness evolution improves an LLM agent's prompts, tools, and workflow, while the optimizer's own tools and procedures often remain fixed. We study whether an optimizer can improve another agent more effectively by also improving how it diagnoses failures, develops edits, and tests their effects. Two observations guide our design. In a controlled study, optimizer self-evolution fails to improve performance without execution-based verification, but achieves the best result of that study when verification is available. Across five executors, self-evolving optimizers build their own tools for failure analysis, verification, training audits, and workflow control. Motivated by these findings, we introduce VERSE, a Verified Self-Evolving optimize
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית