AdviSD：通过多轮自蒸馏学习指导前沿大模型
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
AdviSD让小模型指导大模型，在Gemini和Claude上效果显著，还不需额外计算资源。
AdviSD方法通过可训练的小型顾问模型使用自然语言指导冻结的语言模型执行器。该方法结合基于结果的强化学习和选择性自蒸馏，在BFCL-v3基准上超越advisor-GRPO 4.2-6.4个百分点，在EnvScaler上领先3.9-5.1分。训练后的顾问模型能推广到领域外任务，并能在不同执行器版本和模型家族间迁移。
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advisor can use feedback from completed interactions to improve its advice. However, a plausible correction need not change execution, yet learning from such corrections can still affect the advisor's future decisions in other contexts. In a shared-parameter model, we prove that such corrections can limit learning if their targets favor useful advice less strongly than those of other corrections. Keeping them less often than the rest improves the model's eventual performance compared to learning from every correction. Motivated by this, our method, Advisor Self-Distillation (AdviSD), pairs outcome-based reinforcement learning with self-distillation from a feedback-conditioned copy of the advisor selectively. Reflection proposes corrections, and the advisor scores the same recorded executor response with and without its issued advice, using the magnitude of the difference to select decisions for supervision. This approach does not require executor likelihoods or additional executor rollouts. Experiments with Qwen3-8B advisors for Gemini and Claude show that AdviSD outperforms advisor-GRPO by 4.2-6.4 percentage points on BFCL-v3 and by 3.9-5.1 score points on EnvScaler. The trained advisors generalize to out-of-domain tasks and transfer across different executor versions and model families. AdviSD also beats matched-count random selection, supporting the value of its selection rule.