7 papers
Towards Compositional Generalization in LLMs for Smart Contract Security: A Case Study on Reentrancy Vulnerabilities
Ying Zhou, Jiacheng Wei, Yu Qi +2
Large language models (LLMs) demonstrate remarkable capabilities in natural language understanding and generation. Despite being trained on large-scale, high-quality data, LLMs sti…
Preference-Guided Reinforcement Learning for Efficient Exploration
Guojian Wang, Jianxiang Liu, Xinyuan Li +4
In this paper, we investigate preference-based reinforcement learning (PbRL), which enables reinforcement learning (RL) agents to learn from human feedback. This is particularly va…
A Lightweight Framework for Trigger-Guided LoRA-Based Self-Adaptation in LLMs
Jiacheng Wei, Faguo Wu, Xiao Zhang
Large language models are unable to continuously adapt and learn from new data during reasoning at inference time. To address this limitation, we propose that complex reasoning tas…
Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood
Qingmao Yao, Zhichao Lei, Tianyuan Chen +5
Offline Reinforcement Learning (RL) struggles with distributional shifts, leading to the -value overestimation for out-of-distribution (OOD) actions. Existing methods address th…
Policy Optimization with Smooth Guidance Learned from State-Only Demonstrations
Guojian Wang, Faguo Wu, Xiao Zhang +1
The sparsity of reward feedback remains a challenging problem in online deep reinforcement learning (DRL). Previous approaches have utilized offline demonstrations to achieve impre…
Trajectory-Oriented Policy Optimization with Sparse Rewards
Guojian Wang, Faguo Wu, Xiao Zhang
Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely acco…