Newest papers

GuideEvolve: Self-Evolving Agent Framework with Expert Guidance and 3Ts Mechanisms

美虹 賈, Yasemin Timar, Jonathan Taws · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30017 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

この研究では、専門家の指導と3つの自主的な規制メカニズムを組み込む自己進化するエージェントフレームワーク「ガイドエヴォルブ」を紹介し、3Ts:Think Fast and Slow, Throwback, and Termination by choice. The framework addresses critical limitations in existing self-evolving agent paradigms through dual innovations: (1) a task-specific expert-evaluation-driven evolutionary pipeline, and (2) the integration of 3Ts mechanisms to facilitate cognitive optimization, performance recovery via temporal rollback, and adaptive termination protocols. Empirical validation across the MGSM and MMLU benchmarks demonstrates that GuideEvolve achieves performance metrics comparable to current state-of-the-art models (89.8% accuracy versus

Machine translation (Meta M2M100); the English original follows.

Abstract

This study introduces GuideEvolve, a self-evolving agent framework incorporating expert guidance and three autonomous regulatory mechanisms, collectively termed the 3Ts: Think Fast and Slow, Throwback, and Termination by choice. The framework addresses critical limitations in extant self-evolving agent paradigms through dual innovations: (1) a task-specific expert-evaluation-driven evolutionary pipeline, and (2) the integration of 3Ts mechanisms to facilitate cognitive optimization, performance recovery via temporal rollback, and adaptive termination protocols. Empirical validation across the MGSM and MMLU benchmarks demonstrates that GuideEvolve attains performance metrics comparable to current state-of-the-art models (89.8% accuracy versus Gödel Agent's 90.6% on MGSM; 89.1% versus 87.9% on MMLU), while exhibiting notably reduced variance (25-59%) and enhanced robustness. Furthermore, the framework achieves a 100% evolution success rate, superior to the baseline's 82%, diminishes required optimization iterations by approximately 50% (from 30 iterations in baseline to 15.1 and 13.4 across tasks), and provides improved stability for production deployment.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Extant taxon, Variance (accounting), Dual (grammatical number), Baseline (sea), Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange