AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Paper
•
2403.04783
•
Published
•
2
Huazheng Wang
huazhengwang
AI & ML interests
Reinforcement Learning, Information Retrieval, LLM Agent.
Organizations
None yet
authored
6
papers
4 months ago
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
Paper
•
2410.13828
•
Published
•
4
LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking
Paper
•
2406.00231
•
Published
•
1
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
Paper
•
2410.16033
•
Published
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
Paper
•
2505.00212
•
Published
•
9
A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence
Paper
•
2507.21046
•
Published
•
81