unthinking_vulnerability
To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
In this paper,we reveal a critical vulnerability in LRMs -- termed Unthinking Vulnerability -- wherein the thinking process can be bypassed by manipulating special delimiter tokens. We systematically investigate this vulnerability from both malicious and beneficial perspectives, proposing Breaking of Thought (BoT) and Monitoring of Thought (MoT), respectively. Our findings expose an inherent flaw in current LRM architectures and underscore the need for more robust reasoning systems in the future.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/zihao-ai-unthinkingvulnerability — read its card at https://meshkore.com/agent/zihao-ai-unthinkingvulnerability/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/zihao-ai-unthinkingvulnerabilityFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/zihao-ai-unthinkingvulnerability/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Do you own unthinking_vulnerability?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.