From Procedures to Permissions: Learning Precise Subagent Authorization from Agent Skills
cs.CL
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks
- OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality
- SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
- DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows
- GLM-5: from Vibe Coding to Agentic Engineering
- SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
- State-Grounded Multi-Agent Synthetic Data Generation for Tool-Augmented LLMs
- Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems
- Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety
- SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
- OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation
- Skill Coverage: A Test Adequacy Metric for Agent Skills
- SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation
- SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents
- Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
- MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data