Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jinyu Hou

Jinyu Hou

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

AI×4Crypto×3ML×2Multiagent×2Robotics×1

Frequent co-authors

Chaozhuo Li3×
Litian Zhang3×
Bingyu Yan2×
Xiaoming Zhang2×
Ziyi Zhou2×
Yiming Hei2×

Research Timeline

2026
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

ClawKeeper is a comprehensive, multi-layered security framework designed to mitigate critical vulnerabilities in autonomous agent runtimes like OpenClaw by enforcing protection across skills, plugins, and system state.

PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation

PropGuard introduces a propagation-aware framework to safeguard LLM-MAS against malicious attacks by constructing a dual-view graph, identifying suspicious propagation paths, and applying source-guided remediation.

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS

Evo-Attacker introduces a memory-augmented reinforcement learning framework to perform generalized, long-horizon tool attacks on LLM-MAS, significantly outperforming existing methods.

Critique of Agent Model

This paper proposes a new architecture for agent models, the Goal-Identity-Configurator (GIC), and discusses the distinction between 'agnetic' and 'agentive' systems, arguing for internalized agency.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.LGcs.MATheoreticalRecentJun 22, 2026

Critique of Agent Model

Eric Xing, Mingkai Deng, Jinyu Hou

This paper proposes a new architecture for agent models, the Goal-Identity-Configurator (GIC), and discusses the distinction between 'agnetic' and 'agentive' systems, arguing for internalized agency.

View →
cs.CRcs.AIcs.MARecent
May 25, 2026

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS

Bingyu Yan, Xiaoming Zhang, Jinyu Hou, Chaozhuo Li +3 more

Evo-Attacker introduces a memory-augmented reinforcement learning framework to perform generalized, long-horizon tool attacks on LLM-MAS, significantly outperforming existing methods.

View →
cs.LGcs.AIcs.CRRecentMay 8, 2026

PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation

Bingyu Yan, Xiaoming Zhang, Jinyu Hou, Chaozhuo Li +3 more

PropGuard introduces a propagation-aware framework to safeguard LLM-MAS against malicious attacks by constructing a dual-view graph, identifying suspicious propagation paths, and applying source-guide…

View →
cs.CRcs.AIRecentMar 25, 2026

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

Songyang Liu, Chaozhuo Li, Chenxu Wang, Jinyu Hou +7 more

ClawKeeper is a comprehensive, multi-layered security framework designed to mitigate critical vulnerabilities in autonomous agent runtimes like OpenClaw by enforcing protection across skills, plugins,…

View →