7 papers
GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation
Yuxiao Ye, Yiwen Zhang, Huiyuan Xie +2
LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual model capabilities, but also o…
Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization
Xin Yu, Liuchen Liao, Yiwen Zhang +3
On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has…
Jailbreaking LLMs via Semantically Relevant Nested Scenarios with Targeted Toxic Knowledge
Ning Xu, Bo Gao, Hui Dou
Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks. However, they remain exposed to jailbreak attacks, eliciting harmful responses. The nested…
DemoTuner: Automatic Performance Tuning for Database Management Systems Based on Demonstration Reinforcement Learning
Hui Dou, Lei Jin, Yuxuan Zhou +3
The performance of modern DBMSs such as MySQL and PostgreSQL heavily depends on the configuration of performance-critical knobs. Manual tuning these knobs is laborious and ineffici…
Adjusting the Output of Decision Transformer with Action Gradient
Rui Lin, Yiwen Zhang, Zhicheng Peng +1
Decision Transformer (DT), which integrates reinforcement learning (RL) with the transformer model, introduces a novel approach to offline RL. Unlike classical algorithms that take…
ToMPO: Training LLM Strategic Decision Making from a Multi-Agent Perspective
Yiwen Zhang, Ziang Chen, Fanqi Kong +2
Large Language Models (LLMs) have been used to make decisions in complex scenarios, where they need models to think deeply, reason logically, and decide wisely. Many existing studi…
FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation
Hongda Zhu, Yiwen Zhang, Bing Zhao +6
Large Language Models (LLMs) have made significant strides in front-end code generation. However, existing benchmarks exhibit several critical limitations: many tasks are overly si…