arXiv (All)
open access
Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents
Command-Line Interface (CLI) agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risks during multi-turn interactions with external environments. Existing safety mechanisms mainly rely on external guardrai
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent#300005
- Agent Safety From Within: Detecting Harmful Trajectories from LLM Internal States#1117751
- Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents#1155335
- Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies#299821
- ForesightSafety-SAGE:A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents#800068
Record · ID 1215418
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive