AERO：通过内生双环反馈实现自主进化推理优化
AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback
AI总结：
AERO通过内生双环反馈机制实现自主进化推理优化，提升模型在多个基准测试中的性能表现。
摘要：
大型语言模型（LLMs）在复杂推理方面取得了显著成功，但仍然受到依赖专家标注数据和外部验证者限制的瓶颈。尽管现有自我进化范式旨在绕过这些限制，但它们往往无法识别最优学习区，并且通过错误的内部反馈风险强化集体幻觉和错误先验。为了解决这些挑战，我们提出了AERO，一种无监督框架，通过内化自我提问、回答和批评，在协同的双环系统中实现自主推理进化。受“最近发展区（ZPD）”理论的启发，AERO利用基于熵的位置定位以瞄准“可解性差距”，并采用独立反事实校正进行稳健验证。此外，我们引入了阶梯训练策略，以同步功能角色之间的能力增长并防止课程崩溃。在九个涵盖三个领域的基准测试中，AERO在Qwen3-4B-Base上实现了平均性能提升4.57%，在Qwen3-8B-Base上实现了5.10%的提升，优于竞争基线。代码可在https://github.com/mira-ai-lab/AERO上获得。
英文摘要：
Large Language Models (LLMs) have achieved significant success in complex reasoning but remain bottlenecked by reliance on expert-annotated data and external verifiers. While existing self-evolution paradigms aim to bypass these constraints, they often fail to identify the optimal learning zone and risk reinforcing collective hallucinations and incorrect priors through flawed internal feedback. To address these challenges, we propose \underline{A}utonomous \underline{E}volutionary \underline{R}easoning \underline{O}ptimization (AERO), an unsupervised framework that achieves autonomous reasoning evolution by internalizing self-questioning, answering, and criticism within a synergistic dual-loop system. Inspired by the \textit{Zone of Proximal Development (ZPD)} theory, AERO utilizes entropy-based positioning to target the ``solvability gap'' and employs Independent Counterfactual Correction for robust verification. Furthermore, we introduce a Staggered Training Strategy to synchronize capability growth across functional roles and prevent curriculum collapse. Extensive evaluations across nine benchmarks spanning three domains demonstrate that AERO achieves average performance improvements of 4.57\% on Qwen3-4B-Base and 5.10\% on Qwen3-8B-Base, outperforming competitive baselines. Code is available at https://github.com/mira-ai-lab/AERO.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
