Jiong Lou
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Obsessive Experience Poisoning (OEP), a low-privilege black-box attack that poisons self-evolving LLM agents by generating locally correct but harmful experiences, causing dangerous over-generalization during reflection.
This paper proposes an efficient human intervention mechanism, Deep Interaction, for correcting reasoning errors in large language models, achieving over 25% improvement in correction success rate and reducing token usage by approximately 40%.
Papers
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Hefeng Zhou, Jinxuan Zhang, Jiong Lou, Yuxin Liu +3 more
This paper proposes an efficient human intervention mechanism, Deep Interaction, for correcting reasoning errors in large language models, achieving over 25% improvement in correction success rate and…