Publications (20)
SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph
Jiazheng Li, Yawei Wang, David Yan +5
Large Language Models (LLMs) have demonstrated remarkable capabilities, enabling language agents to excel at single-turn tasks. However, their application to complex, multi-step, a…
Reward function shape exploration in adversarial imitation learning: an empirical study
Yawei Wang, Xiu Li
For adversarial imitation learning algorithms (AILs), no true rewards are obtained from the environment for learning the strategy. However, the pseudo rewards based on the output o…
Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration
Ming Zhang, Yawei Wang, Xiaoteng Ma +4
The generative adversarial imitation learning (GAIL) has provided an adversarial learning framework for imitating expert policy from demonstrations in high-dimensional continuous t…
RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation
Zhichao Xu, Minheng Wang, Yawei Wang +4
Search agents trained with reinforcement learning (RL) interleave reasoning with tool calls in a multi-turn, tool-integrated reasoning (TIR) loop, where each tool invocation return…
Fully superconducting machine for electric aircraft propulsion: study of AC loss for HTS stator
Fangjing Weng, Min Zhang, Tian Lan +2
Fully superconducting machines provide the high power density required for future electric aircraft propulsion. However, superconducting windings generate AC losses in AC electrica…
Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
Dongkyu Derek Cho, Huan Song, Arijit Ghosh Chowdhury +6
Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment…
A Sober Look at Agentic Misalignment in Automated Workflows
Wenqian Ye, Bo Yuan, Zhichao Xu +4
We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Although these systems can solv…
Reinforcement Learning for Self-Improving Agent with Skill Library
Jiongxiao Wang, Qiaojing Yan, Yawei Wang +6
Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt wh…
Uncovering Causal Relation Shifts in Event Sequences under Out-of-Domain Interventions
Kazi Tasnim Zinat, Yun Zhou, Xiang Lyu +3
Inferring causal relationships between event pairs in a temporal sequence is applicable in many domains such as healthcare, manufacturing, and transportation. Most existing work on…
Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning
Wenhao Zhang, Yibo Xie, Rui Wang +9
Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models. Reusing each rollout batch for additional learner updates amort…
SDRT: Enhance Vision-Language Models by Self-Distillation with Diverse Reasoning Traces
Guande Wu, Huan Song, Yawei Wang +4
Reasoning is increasingly crucial for various tasks. While chain-of-thought prompting enables large language models to leverage reasoning effectively, harnessing the reasoning capa…
3D quench modeling based on T-A formulation for high temperature superconductor CORC cables
Yawei Wang, Jinxing Zheng, Zixuan Zhu +2
High temperature superconductor (HTS) (RE)Ba2Cu3Ox (REBCO) conductor on round core cable (CORC) has high current carrying capacity for high field magnet and power applications. In…
A Systematic Survey of Blockchained Federated Learning
Zhilin Wang, Qin Hu, Minghui Xu +3
With the technological advances in machine learning, effective ways are available to process the huge amount of data generated in real life. However, issues of privacy and scalabil…
Hybrid roles of adaptation and optimization in formation of vascular network
Yawei Wang, Zilu Qin, Yubo Fan
It was hypothesized that the structures of biological transport networks are the result of either energy consumption or adaptation dynamics. Although approaches based on these hypo…
CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection
Linbo Liu, Guande Wu, Han Ding +7
Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineering approaches primarily rely on…
Autonomous Charging of Electric Vehicle Fleets to Enhance Renewable Generation Dispatchability
Reza Bayani, Saeed D. Manshadi, Guangyi Liu +2
A total 19% of generation capacity in California is offered by PV units and over some months, more than 10% of this energy is curtailed. In this research, a novel approach to reduc…
Diversity-aware Web APIs Recommendation with Compatibility Guarantee
Wenwen Gonga, Yulan Zhang, Xuyun Zhang +4
With the ever-increasing prevalence of web APIs (Application Programming Interfaces) in enabling smart software developments, finding and composing a list of existing web APIs that…
A Systematic Survey of Automatic Prompt Optimization Techniques
Kiran Ramnath, Kang Zhou, Sheng Guan +18
Since the advent of large language models (LLMs), prompt engineering has been a crucial step for eliciting desired responses for various Natural Language Processing (NLP) tasks. Ho…
Diversified and Compatible Web APIs Recommendation in IoT
Wenwen Gong, Huiping Wu, Xiaokang Wang +4
With the ever-increasing popularity of Service-oriented Architecture (SoA) and Internet of Things (IoT), a considerable number of enterprises or organizations are attempting to enc…
Reinforcement Mid-Training
Yijun Tian, Shaoyu Chen, Zhichao Xu +4
The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an addit…