ATLAS：一种用于EvoDPO的多LLM训练框架，具有自适应参考进化
ATLAS: A Multi-LLM Training Framework for EvoDPO with Adaptive Reference Evolution
AI总结：
本文提出ATLAS框架，通过自适应参考进化解决多LLM代理系统中固定参考模型导致的更新保守或训练停滞问题，结合支持者驱动探索与EvoDPO驱动的稳定性，提升长期评估驱动的自我改进能力。
摘要：
最近的多LLM代理系统在自动化问题解决中表现出有前途的能力，但它们主要依赖于冻结的代理或静态微调管道。为了解决这一限制，我们的主要贡献是ATLAS（用于代理自演化的自适应任务分布式学习），一种多代理框架，其中专门的元代理协作训练和优化一个活跃的代理以获得领域特定的策略。在这些管道中的迭代偏好学习中的核心挑战是依赖于固定的参考模型，通常导致过于保守的更新或训练停滞。为克服这一问题，该框架的算法引擎使用进化直接偏好优化（EvoDPO）。EvoDPO采用一个检查代理，根据连续的训练 telemetry 进行自适应的、基于代理-KL门控的参考策略更新。我们评估了该完整框架在一系列具有挑战性的环境中，包括非平稳的上下文带仔、偏微分方程（PINNs）和组合优化任务（TSP、Bin Packing）。通过与固定参考、自适应参考和外部自动发现基线的比较，我们的结果表明，ATLAS结合支持者驱动的探索与EvoDPO驱动的稳定性，以提高长期评估驱动的自我改进能力。
英文摘要：
Recent multi-LLM agent systems have shown promising capabilities for automated problem-solving, yet they predominantly rely on frozen agents or static fine-tuning pipelines. To address this limitation, our primary contribution is ATLAS (Adaptive Task-distributed Learning for Agentic Self-evolution), a multi-agent framework where specialized meta-agents collaboratively train and refine an active agent toward a domain-specific policy. A core challenge in iterative preference learning within these pipelines is the reliance on fixed reference models, which typically leads to overly conservative updates or training stagnation. To overcome this, the framework's algorithmic engine utilizes Evolving Direct Preference Optimization (EvoDPO). EvoDPO employs an inspection agent to perform adaptive, proxy-KL gated reference policy updates based on continuous training telemetry. We evaluate this full framework across a diverse set of challenging environments-including non-stationary contextual bandits, partial differential equations (PINNs), and combinatorial optimization tasks (TSP, Bin Packing). Through comparison against fixed-reference, adaptive-reference, and external automated-discovery baselines, our results suggest that ATLAS combines supporter-driven exploration with EvoDPO-driven stability to improve long-horizon evaluator-driven self-improvement.
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。
