arXiv AI
1d ago
Bounded Agents: Delegation Security for Multi-Agent AI Systems
arXiv:2608. 15888v1 Announce Type: new Abstract: LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents.
MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures
arXiv:2608. 07556v1 Announce Type: cross Abstract: Multi-agent systems (MAS) decompose long-horizon tasks across supervisors and subagents, but delegated goals do not necessarily carry their original authorization boundaries.
Related stories
arXiv AI
Jun 30
ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
arXiv:2605. 26542v2 Announce Type: replace-cross Abstract: Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime.
arXiv AI
Aug 5
WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks
arXiv:2608. 03499v1 Announce Type: new Abstract: Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations.
arXiv AI
Aug 11
Multi-Agent AI Safety as an Institutional Design Problem
arXiv:2608. 09828v1 Announce Type: cross Abstract: AI agents increasingly work inside systems that govern how they delegate tasks, move information, execute actions, and use shared resources.
Hugging Face Trending Papers
Aug 4
WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks
Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners.
arXiv AI
Jul 7
Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies
arXiv:2607. 03423v1 Announce Type: cross Abstract: Modern AI agent implementations such as frontier coding agents chain multiple tools at runtime that create a security surface that per-tool guardrails are unable to address, as individually permitted tools can violate organizational policies when composed.
arXiv AI
Jul 1
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
arXiv AI
Jul 28
Decentralized Granular Access Control for Agentic AI Systems in Critical Infrastructure
arXiv:2607. 22611v1 Announce Type: new Abstract: The deployment of autonomous AI agents in production infrastructure introduces fundamental security challenges that traditional role-based access control (RBAC) models cannot address.
arXiv AI
Jul 14
Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents
arXiv:2607. 10487v1 Announce Type: cross Abstract: LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result.
arXiv AI
Jun 30
Choose Your Agent: Tradeoffs in Adopting AI Advisors, Coaches, and Delegates in Multi-Party Negotiation
arXiv:2602. 12089v3 Announce Type: replace-cross Abstract: As AI usage becomes more prevalent in social contexts, understanding agent-user interaction is critical to designing systems that imp rove both individual and group outcomes.
arXiv AI
1d ago
A Policy Algebra for Trust-Preserving Agentic AI Execution
arXiv:2608. 16402v1 Announce Type: new Abstract: Large language model-based agentic frameworks primarily optimize capability: whether an agent can reason, retrieve information, call tools, delegate work, and complete a goal.
arXiv AI
Jun 6
CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
arXiv:2601. 09923v3 Announce Type: replace Abstract: AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior.