Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
Department of Computer Science and Technology, Tsinghua University, Beijing, China(清华大学计算机科学与技术系);Beijing National Research Center for Information Science and Technology, Beijing, China(北京信息科学国家研究中心)
Large language models (LLMs) have shown strong empirical gains as self-evolving agents for CUDA kernel generation, driven by feedback-conditioned planning across generations. However, how planning decisions attribute and combine heterogeneous feedback signals remains opaque. Standard end-to-end ablations fail to resolve this question, as iterative planning amplifies early perturbations and conflates feedback effects with trajectory-dependent drift.
We introduce \texttt{CUDAnalyst}, a unified analysis layer for controlled, generation-level attribution of planning decisions to feedback components via trajectory freezing and selective feedback injection. \texttt{CUDAnalyst} enables stable generation-level evaluation and principled coalitional-style attribution of feedback effects and interactions. Our results show that explicit planning is beneficial only when feedback is aligned, that effective planning emerges from structured multi-feedback interactions, and that high-level plans from stronger reasoning models can partially transfer to weaker ones. These trends hold across reference backbones, representative workloads, and reference induction regimes, indicating that the identified feedback-to-plan structure is robust within the controlled axes studied.
From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum Learning
Zhejiang University(浙江大学);Tianjin University(天津大学);Qingdao University(青岛大学);Shanghai Jiao Tong University(上海交通大学);National University of Singapore(新加坡国立大学)
Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy
Institute for Artificial Intelligence(人工智能研究院);Computer School(计算机学院);School of Artificial Intelligence(人工智能学院);Center on Frontiers of Computing Studies(计算前沿研究中心);State Key Laboratory of General Artificial Intelligence(通用人工智能国家重点实验室);Nat’l Eng. Research Center of Visual Technology(视觉技术国家工程研究中心);State Key Lab of General Artificial Intelligence(通用人工智能国家重点实验室);BIGAI
Evolving and Executing Research Plans via Double-Loop Multi-Agent Collaboration
Department of Computing, The Hong Kong Polytechnic University(香港理工大学计算机系);FireTorch Partners(FireTorch合作伙伴);College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机科学与软件工程学院)
CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning
Institute of Artificial Intelligence, Xiamen University(厦门大学人工智能学院);Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism(文化和旅游部闽台非物质文化遗产数字化保护与智能处理重点实验室(厦门大学));Zhejiang University(浙江大学);Alibaba Group(阿里巴巴集团)
HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research
Peking University(北京大学);The University of Hong Kong(香港大学);The Hong Kong University of Science and Technology(香港科技大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)