DITTO uses RL with verbal feedback to train LLMs for human behavior simulation, reporting 36% average gains over base models and outperforming GPT-5.4 on 6 of 10 SOUL benchmark tasks.
Haicosystem: An ecosystem for sandboxing safety risks in human-ai interactions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The paper introduces a taxonomy of security risks in cloud-hosted tool-enabled AI agents arising mainly from over-privileged tools and authority leakage, supported by scenarios, mitigations, and a small experiment.
citing papers explorer
-
Reinforcing Human Behavior Simulation via Verbal Feedback
DITTO uses RL with verbal feedback to train LLMs for human behavior simulation, reporting 36% average gains over base models and outperforming GPT-5.4 on 6 of 10 SOUL benchmark tasks.
-
Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments
The paper introduces a taxonomy of security risks in cloud-hosted tool-enabled AI agents arising mainly from over-privileged tools and authority leakage, supported by scenarios, mitigations, and a small experiment.