Guibin Zhang
Guibin Zhang has 3 papers in our library, in 2025–2026; often with Guancheng Wan, Kun Wang, Bingli Wu.
OpenAlex · ORCID · h-index 18 · 140 works · 1,538 citations OpenAlex, 2026-10-14
📄 3 works in our library · 🔗 Cited 42 times in our library · ⭐ Paper Stars ranking: #7388
Affiliations
🎓China University of Geosciences (Beijing)Beijing ·
China2000–2025 · 53 papers🎓Chongqing Jiaotong UniversityChongqing ·
China2024–2025 · 4 papers🏥Hebei General HospitalShijiazhuang ·
China2020–2025 · 4 papers🔬Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)Guangzhou ·
China2024–2025 · 4 papers🎓Tongji UniversityShanghai ·
China2024–2025 · 4 papers🎓Xidian UniversityXi'an ·
China2024–2025 · 4 papers🎓Peking UniversityBeijing ·
China2022–2025 · 2 papers🎓Haojing College of Shaanxi University of Science and TechnologyXianyang ·
China2025 · 1 paper🎓Yancheng Institute of TechnologyYancheng ·
China2025 · 1 paper🎓China University of GeosciencesWuhan ·
China2000–2024 · 11 papers
Fields, topics and concepts
📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArtificial Intelligence · 3 worksArts and Humanities · 2 worksLanguage and Linguistics · 2 worksSocial Sciences · 1 workInformation Systems · 1 workSociology and Political Science · 1 work
Works by year
2020s
Papers
- MasRouter: Learning to Route LLMs for Multi-Agent Systems (2025 · 35 citations)
LLM-based multi-agent systems (MAS) often outperform single agents, but they consume many tokens. Existing LLM routers choose one model per query, so they only fit single-agent setups. They ignore how agents should cooperate and which roles they should play. The authors formalize this broader task as Multi-Agent… - G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems (2025 · 30 citations)
Multi-agent systems built on LLMs inherit the weaknesses of single agents. They also gain a new one: a compromised agent can spread misinformation or malicious instructions through inter-agent communication until much of the system is corrupted. G-Safeguard defends against this by treating the system's communication… - EvoRoute: Experience-Driven Self-Routing LLM Agent Systems (2026 · 2 citations)
Multi-model agentic systems for deep research perform well but often run slowly and cost a lot. The authors frame this as the Agent System Trilemma : it is hard to get high accuracy, low monetary cost and fast completion at the same time. Their solution, EvoRoute , chooses an LLM backbone for every individual step of…
Co-authors here
- Guancheng Wan ×2
- Kun Wang ×2
- Bingli Wu
- Fei Huang
- Haiyang Yu
- Shuicheng Yan
- Yang Wang
- Yanwei Yue
- Yiyan Qi
- Yongbin Li
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/guibin-zhang/