English(EN)Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting
新框架通过减轻过拟合和改进验证来增强LLM的自我演化
作者PulseAugur 编辑部·[7 个来源]·
研究人员正在开发新框架以增强大型语言模型（LLM）的自我演化能力。SkillBoost是一个三阶段框架，旨在通过结合结构化利用失败、先验指导探索以及验证接受候选修复来减轻技能过拟合。另一种方法Skill Self-Play（Skill-SP）使用一个包含提议者、求解器和技能控制器的协同演化框架，以平衡任务多样性和验证可靠性。此外，具有自可验证奖励的强化学习（RLSVR）将开放式任务转化为可验证的代理环境，以实现LLM在确定性正确性领域之外的自我改进。
AI
arXiv:2607.26643v1 Announce Type: cross Abstract: Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions remains a central challenge in real-world applications. A promising solution is to treat skills as trainable states and optimize …
Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions remains a central challenge in real-world applications. A promising solution is to treat skills as trainable states and optimize them in the same way as model parameters in neural…
arXiv cs.AI
TIER_1English(EN)·Qinsi Wang, Jing Shi, Huazheng Wang, Kun Wan, Yiran Wu, Bo Liu, Qingyun Wu, Hai Helen Li, Yiran Chen, Handong Zhao, Wentian Zhao·
arXiv:2607.23802v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent progress in reasoning-oriented large language models (LLMs) by enabling large-scale optimization. However, its applicability remains largely limited to domains …
arXiv:2607.22529v1 Announce Type: new Abstract: LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task diversity and verification reliability: environment…
arXiv:2607.21971v1 Announce Type: cross Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains. We hypothesize that the success of such evolution frameworks hinges on meta-skills, …
LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task diversity and verification reliability: environment-bound methods obtain precise feedback but confi…
<h2> What Changed </h2> <p>For years, the paradigm of Large Language Model (LLM) training has relied heavily on human-curated datasets and manual annotation. While effective, this approach is fundamentally limited by the scalability of human effort and the static nature of the re…
