9 papers
Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution
Yubin Lyu, Fu Li, Jiawei Fei +3
Optimizing deployed AI systems increasingly amounts to editing prompts, skills, harnesses, and code rather than model weights. Existing approaches commonly optimize these artifacts…
Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair
Mehdi Bahrami, Kosaku Kimura, Satoshi Munakata +24
Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long horizons, tool-use discipline…
Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
Bochao Liu, Zhipeng Qian, Yang Zhao +10
Operating and maintaining (O&M) large-scale online engine systems (eg, search, recommendation and advertising) demands substantial human effort for release monitoring, alert respon…
MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory
Yang Zhao, Chengxiao Dai, Mengying Kou +1
Agentic memory evolves across tasks into durable derived artifacts: summaries, cached outputs, embeddings, learned skills, and executable tool procedures. When a source artifact is…
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Guanting Dong, Junting Lu, Junjie Huang +17
Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and bro…
AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculum
Jiaqi Li, Lvyang Zhang, Yang Zhao +2
What does it mean to give an AI agent a complete education? Current agent development produces specialists systems optimized for a single capability dimension, whether tool use, co…
ShardMemo: Scope-Before-Routing for Agentic Memory Retrieval
Yang Zhao, Chengxiao Dai, Mengying Kou +2
Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constraints: which memories it is permi…
CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering
Yang Zhao, Chengxiao Dai, Wei Zhuo +2
Knowledge graphs provide structured context for multi-hop question answering, but deployed systems must balance answer accuracy with strict latency and cost targets while preservin…
A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy
Yang Zhao, Chengxiao Dai, Dusit Niyato +7
Large language models (LLMs) hold promise for sustainable manufacturing, but often hallucinate industrial codes and emission factors, undermining regulatory and investment decision…