HACE:異質智能體協同演化框架
Heterogeneous Agentic Coevolution
HACE 框架共同演化專門化基礎模型與 LLM 智能體,在推薦、蛋白質功能預測及晶體穩定性預測三個領域的主要任務指標上,勝過受評估的自我改進方法。框架以監督式學習提升專家模型,並以當前專家模型經核實的效能提升引導智能體進行 on-policy 強化式自我訓練,再以演化搜尋優化兩者的資訊交流及訓練經驗選取方式。
Published on Oct 12
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
HACE is a framework that jointly evolves specialized foundation models and LLM agents through reciprocal learning and evolutionary optimization of their interaction harness, improving performance across recommendation, protein prediction, and materials discovery.
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.
View arXiv page View PDF Project page Add to collection
Get this paper in your agent:
hf papers read 2610.16078
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.16078 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.16078 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.16078 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co