MemScope: Evolving Agent Memory Architectures through Localized Code Repair
State Key Laboratory of AI Safety(人工智能安全国家重点实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Meituan(美团)
Miao Su, Yucan Guo, Zixuan Li, Long Bai, Zhongni Hou, Xiaolong Jin, Jiafeng Guo
Agent memory architectures define how LLM agents store and reuse experience across tasks, but they are typically fixed after deployment, limiting their adaptability across task types. Recent self-evolving approaches instead adapt these memory architectures using execution feedback, typically represented as evaluation scores or compressed summaries. However, such coarse-grained feedback is insufficient for precise failure localization in current agent systems, where long-horizon task execution involves multiple interacting components. Without a precise failure location, existing approaches lack a clear code-level target for modification, leaving the update scope weakly constrained and often leading to large-scale rewrites of an otherwise capable memory architecture. We propose MemScope, a framework for evidence-grounded, localized evolution of an existing memory architecture. Its tool-using Patch Agent jointly inspects raw execution traces, runtime memory state, and current architecture code to identify repair targets and apply bounded, in-place edits under provider-identity and memory-compatibility constraints. On GAIA, the trace-and-memory inspection variant achieves 86.67% accuracy, compared with 70.00% for trace-only and 63.33% for summary-only feedback. Under xBench tasks, the evolved memory architecture improves over its original version from 49 to 55 correct answers with DeepSeek V3.2 and from 50 to 53 with Kimi K2.7 Code. On disjoint ALFWorld unseen tasks, success rises from 50.75% to 71.64%. Across archived architecture-snapshot transitions, the median code-change ratio is 4.4%. These results support fine-grained execution evidence as a basis for localized, in-place memory-architecture evolution.
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems
Shanghai Jiao Tong University(上海交通大学);Eastern Institute of Technology(东部技术研究所);University of Science and Technology of China(中国科学技术大学);Southeast University(东南大学);Ningbo Institute of Digital Twin(宁波数字孪生研究所)
REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
Engineering Center for Space Utilization of Chinese Academy of Sciences(中国科学院空间利用工程技术中心);University of Chinese Academy of Sciences(中国科学院大学);School of Computer Science and Engineering(计算机科学与工程学院);Northeastern University(东北大学);New York University(纽约大学);School of Computing(计算机学院);National University of Singapore(新加坡国立大学);The Chinese University of Hong Kong(香港中文大学);Technical University of Munich(慕尼黑技术大学)
Zhejiang University(浙江大学);Huazhong University of Science and Technology(华中科技大学);Xi’an Jiaotong University(西安交通大学);National University of Defense Technology(国防科技大学);Shanghai Jiao Tong University(上海交通大学);Georgia Institute of Technology(佐治亚理工学院);University of Science and Technology of China(中国科学技术大学);Nanyang Technological University(南洋理工大学);OPPO Research Institute(OPPO研究院);Tianjin University(天津大学);Chongqing University(重庆大学);Alibaba Group(阿里巴巴集团);Rakuten Group(乐天集团)
EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Dalian University of Technology(大连理工大学);Fudan University(复旦大学);University of Oxford(牛津大学);North China Electric Power University(华北电力大学);The University of Texas Health Science Center at Houston(德克萨斯大学休斯顿健康科学中心)
Zhejiang University(浙江大学);Alibaba Group(阿里巴巴集团);City University of Hong Kong(香港城市大学);The Hong Kong University of Science and Technology(香港科技大学);University of Michigan(密歇根大学)
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
The Hong Kong University of Science and Technology(香港科学与技术大学);Harbin Institute of Technology(哈尔滨工业大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Nanjing University(南京大学);The University of Hong Kong(香港大学)
COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
Carnegie Mellon University(卡内基梅隆大学);University of Southern California(南加州大学);Singapore University of Technology and Design(新加坡科技设计大学);University of Arizona(亚利桑那大学)
SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
Ray and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University(卡内基梅隆大学计算机科学学院Ray and Stephanie Lane计算生物学系);Machine Learning Department, School of Computer Science, Carnegie Mellon University(卡内基梅隆大学计算机科学学院机器学习系)
Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents
Chengdu Institute of Computer Applications, Chinese Academy of Sciences(中国科学院成都计算机应用研究所);University of Chinese Academy of Sciences(中国科学院大学);Beijing Institute of Technology(北京理工大学);Beijing University of Technology(北京工业大学);Yangtze Delta Region Institute of Tsinghua University, Zhejiang(浙江清华大学长三角研究院);Jiaxing Key Laboratory of Artificial Intelligence and Cyber Resilience(嘉兴人工智能与网络安全重点实验室)
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
The Chinese University of Hong Kong(香港中文大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));South China University of Technology(华南理工大学);Xiamen University(厦门大学);Peking University(北京大学);The Hong Kong University of Science and Technology(香港科学与技术大学);The University of Hong Kong(香港大学)
SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?
Shanghai Jiao Tong University(上海交通大学);Beijing University of Posts and Telecommunications(北京邮电大学);Independent Researcher(独立研究者);Jinan Inspur Data Technology Co., Ltd.(济南 Inspur 数据技术有限公司)
ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning
University of Maryland, Baltimore County(马里兰大学巴尔的摩县分校);University at Buffalo(布法罗大学);University of Colorado Boulder(科罗拉多大学博尔德分校);University of Colorado Colorado Springs(科罗拉多大学科罗拉多州立分校)
Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification
School of Physics and Astronomy, The University of Edinburgh, Edinburgh, UK(物理与天文学院,爱丁堡大学,爱丁堡,英国);State Key Laboratory of Analog and Mixed-Signal VLSI, University of Macau, Macau(模拟与混合信号VLSI国家重点实验室,澳门大学,澳门);School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China(科学与工程学院,香港中文大学(深圳))
SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback
Beijing University of Posts and Telecommunications(北京邮电大学);North China Electric Power University(华北电力大学);Chongqing University of Posts and Telecommunications(重庆邮电大学)