← Back to all news
arXiv AI By Alexander Tu, Michael Tu

Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents

Read the original on arXiv AI →

The paper introduces a post‑training framework that teaches a 4B‑parameter language model to exercise task‑conditioned authority in executable terminal and Model Context Protocol (MCP) environments. By auditing each action across six risk dimensions with deterministic verifiers and optimizing for task‑specific excess‑privilege values, the authors achieve 98.48% safe success and reduce excess‑authority errors from 4.56% to 0.79% on held‑out tasks. The study also demonstrates capability retention, prompt‑directed improvement, and generalization over a 400‑task continuation test.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 25

Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery

The paper introduces skilder, a framework that organizes LLM agent capabilities into role‑scoped bundles of skills, tools, and instructions, with explicit limits. Agents start with a minimal role catalog, discover the roles needed for a task, and receive the associated tools only through a single MCP server, ensuring deterministic enforcement of scope. Experiments on 13 tasks with six models show that skilder’s authorization layer prevents unauthorized tool calls and parameter violations while maintaining flexibility through dynamic cross‑role capability acquisition.

By Michael Stettler, Benjamin Girardet, Jonas Canton, Nicolas Corod
llmsagents
More like this →
arXiv AI
Aug 24

ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents

ClawSentry is an open‑source, framework‑agnostic security supervision gateway designed to protect autonomous large language model (LLM) agents from progressive risks that can arise at four points in the agent control loop: skill admission, invocation‑time intent, execution‑time effect, and post‑action consequence. It introduces a multi‑tier decision engine—deterministic L1, rule‑anchored L2, and read‑only L3—alongside a First‑Use Skill Package Review (FSPR) and an Agent Harness Protocol (AHP) that applies a single policy across multiple agent runtimes without modifying their internals. Evaluation on SkillInject and the SkillsSafety benchmark shows that ClawSentry significantly reduces contextual adversarial skill risk (ASR) while maintaining high task success rates (TSR).

By Kai Wang, Zeming Wei, BiaoJie Zeng, Chang Jin, An Wang, Xiaokun Luan, Zhixiao Lin, Jingjing Qu, Xia Hu, Xingcheng Xu
llmsagentsmultimodalbenchmarks
More like this →
arXiv AI
Sep 15

Empirical Evaluation of Task-Based Permission Scoping Architecture for AI Agents

The paper evaluates a task-based permission scoping architecture for AI agents, comparing a fine‑tuned RoBERTa‑large encoder to few‑shot Claude Haiku 4.5 on a 600‑prompt dataset. It shows the new system achieves comparable macro‑F1 (0.881 vs. 0.886) and higher precision (0.897 vs. 0.842), while reducing severity‑weighted residual risk from 1.12 to 0.63. The study also introduces an attack‑surface elimination metric, demonstrating that task‑granular control can close 84.4% of the severity‑weighted surface, far surpassing role‑based ceilings alone.

By Halil Burak Noyan
llmsagentsfine-tuning
More like this →