会员服务
Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
Arxiv
0+阅读 · 10月31日
Then there is prompt injection, a malicious email, ...: The Wild Wide West of OpenClaw Agentic System Security
Arxiv
0+阅读 · 10月26日
Scope-Gap Injection: Exploiting Evaluator Channel Blind Spots in the OpenClaw Agent Security Competition
Arxiv
0+阅读 · 10月26日
Who Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers
Arxiv
0+阅读 · 10月23日
Foundations for Investigations of Agentic AI Systems from the Forensic Analysis of OpenClaw
Arxiv
0+阅读 · 10月19日
When Approval Becomes Execution: Authorization-Grounded Workflow Attacks on Tool-Using Agents
Arxiv
0+阅读 · 10月16日
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Arxiv
0+阅读 · 10月10日
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents
Arxiv
0+阅读 · 10月10日
TAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories
Arxiv
0+阅读 · 9月29日
TAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories
Arxiv
0+阅读 · 10月1日
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
Arxiv
0+阅读 · 8月28日
Resource Constraints and Performance in Agentic AI Systems
Arxiv
0+阅读 · 8月28日
OpenForgeRL: Train Harness-native Agents in Any Environment
Arxiv
0+阅读 · 8月7日
OpenForgeRL: Train Harness-native Agents in Any Environment
Arxiv
0+阅读 · 7月24日
MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop
Arxiv
0+阅读 · 6月21日
参考链接
微信扫码咨询专知VIP会员
Top