AINeutralarXiv – CS AI · Mar 176/10
🧠
More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists
Research reveals that while increasing the number of LLM agents improves mathematical problem-solving accuracy, these multi-agent systems remain vulnerable to adversarial attacks. The study found that human-like typos pose the greatest threat to robustness, and the adversarial vulnerability gap persists regardless of agent count.
🧠 Llama