Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jiong Lou

Jiong Lou

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Crypto×1ML×1

Frequent co-authors

Jie Li2×
Hefeng Zhou1×
Jinxuan Zhang1×
Yuxin Liu1×
Chaochao Lu1×
Jingjing Qu1×

Research Timeline

2026
OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences

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.

Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models

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%.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentJul 15, 2026

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…

View →
cs.CRcs.AIcs.LGRecent
May 18, 2026

OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences

Kaixiang Wang, Jiong Lou, Zhaojiacheng Zhou, Jie Li

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 dangero…

View →