arXiv cs.AI· Wenqian Ye, Ziwei Guan, Zi Yang, Shivani Modi, Cici Cong Wu, Yunlong He, Yuxin Chen, Zhengyu Zhang, Liang Luo, Venkatesh Ranganathan, Jianhui Sun, Yantao Yao, Wenlin Chen, Buyun Zhang, Ellie Dingqiao Wen, Henry Kautz, Aidong Zhang·· 3 天前AI 评分40
HACE：异构智能体协同进化框架，让专用基础模型与 LLM 智能体互相促进
Heterogeneous Agentic Coevolution
AI 导读
研究者提出异构智能体协同进化框架 HACE，通过相互学习让专用基础模型与 LLM 智能体共同进化：智能体以 on-policy 强化自训练方式学习，并由当前专用模型的已验证性能增益引导，其探索又反过来指导专用模型的监督学习。HACE 还用进化搜索优化两者的交互机制，在推荐系统、蛋白质功能预测和晶体稳定性预测三个领域的主任务指标上均优于所评估的自改进方法。
正文 · 原文
Authors:Wenqian Ye, Ziwei Guan, Zi Yang, Shivani Modi, Cici Cong Wu, Yunlong He, Yuxin Chen, Zhengyu Zhang, Liang Luo, Venkatesh Ranganathan, Jianhui Sun, Yantao Yao, Wenlin Chen, Buyun Zhang, Ellie Dingqiao Wen, Henry Kautz, Aidong Zhang
Abstract:Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence. However, many domain-specific applications rely on specialized foundation models that possess strong domain expertise but remain dependent on human-designed improvements. Extending recursive self-improvement to these models presents a key challenge: as a specialist improves, the strategies used to advance it must also adapt. To address this challenge, we propose Heterogeneous Agentic CoEvolution (HACE), a framework that jointly evolves specialized foundation models and LLM agents through reciprocal learning. HACE improves the specialist through supervised learning while training the agent with on-policy reinforced self-training, guided by verified performance gains on the current specialist. The agent's exploration, in turn, informs subsequent specialist training, enabling both models to adapt to each other's progress. To sustain this reciprocal learning, HACE further employs evolutionary search to optimize their interaction harness, adapting how the models exchange information and select training experiences as their capabilities evolve. We evaluate HACE across three challenging domains: recommendation systems, protein function prediction in biology, and crystal stability prediction in material discovery. We show that HACE outperforms the evaluated self-improving methods on the primary task metrics across all three domains. These results shed light on heterogeneous coevolution as a universal approach to improving specialized foundation models through reciprocal interaction with a learning agent.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16078 [cs.AI] |
| (or arXiv:2610.16078v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16078 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenqian Ye [view email]
[v1]
Mon, 12 Oct 2026 02:34:01 UTC (5,562 KB)
来源：arXiv cs.AI · arxiv.org