180 citations · 286 across the 91 of their papers we have counts for
25 papers · 1 filter
RUBAS: Rubric-Based Reinforcement Learning for Agent Safety
Xian Qi Loye, Qinglin Su, Zhexin Zhang +5
The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text generation. Existing alignment…
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
Junxiao Yang, Haoran Liu, Jinzhe Tu +9
Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We a…
GLM-5: from Vibe Coding to Agentic Engineering
GLM-5-Team, :, Aohan Zeng +184
We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (AR…
Trust-Region Adaptive Policy Optimization
Mingyu Su, Jian Guan, Yuxian Gu +2
Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning…
Data-Efficient RLVR via Off-Policy Influence Guidance
Erle Zhu, Dazhi Jiang, Yuan Wang +8
Data selection is a critical aspect of Reinforcement Learning with Verifiable Rewards (RLVR) for enhancing the reasoning capabilities of large language models (LLMs). Current data…
Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
Junxiao Yang, Zhexin Zhang, Shiyao Cui +2
Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs); however, the transferability of these attacks across different models remains limited.…
Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
Xiaoying Zhang, Jean-Francois Ton, Wei Shen +2
We introduce Adversarial Policy Optimization (AdvPO), a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback (RLHF) for L…
Federated Linear Contextual Bandits with Heterogeneous Clients
Ethan Blaser, Chuanhao Li, Hongning Wang
The demand for collaborative and private bandit learning across multiple agents is surging due to the growing quantity of data generated from distributed systems. Federated bandit…
Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits
Zhiwei Wang, Huazheng Wang, Hongning Wang
Adversarial attacks against stochastic multi-armed bandit (MAB) algorithms have been extensively studied in the literature. In this work, we focus on reward poisoning attacks and f…
Incentivized Truthful Communication for Federated Bandits
Zhepei Wei, Chuanhao Li, Tianze Ren +2
To enhance the efficiency and practicality of federated bandit learning, recent advances have introduced incentives to motivate communication among clients, where a client particip…
Incentivized Communication for Federated Bandits
Zhepei Wei, Chuanhao Li, Haifeng Xu +1
Most existing works on federated bandits take it for granted that all clients are altruistic about sharing their data with the server for the collective good whenever needed. Despi…
Uncertainty-Aware Instance Reweighting for Off-Policy Learning
Xiaoying Zhang, Junpu Chen, Hongning Wang +4
Off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has shown importance in various real-world applications, such as se…
Meta-Reinforcement Learning via Exploratory Task Clustering
Zhendong Chu, Hongning Wang
Meta-reinforcement learning (meta-RL) aims to quickly solve new tasks by leveraging knowledge from prior tasks. However, previous studies often assume a single mode homogeneous tas…
Dynamic Global Sensitivity for Differentially Private Contextual Bandits
Huazheng Wang, David Zhao, Hongning Wang
Bandit algorithms have become a reference solution for interactive recommendation. However, as such algorithms directly interact with users for improved recommendations, serious pr…
Communication Efficient Distributed Learning for Kernelized Contextual Bandits
Chuanhao Li, Huazheng Wang, Mengdi Wang +1
We tackle the communication efficiency challenge of learning kernelized contextual bandits in a distributed setting. Despite the recent advances in communication-efficient distribu…
Learning from a Learning User for Optimal Recommendations
Fan Yao, Chuanhao Li, Denis Nekipelov +2
In real-world recommendation problems, especially those with a formidably large item space, users have to gradually learn to estimate the utility of any fresh recommendations from…
Communication Efficient Federated Learning for Generalized Linear Bandits
Chuanhao Li, Hongning Wang
Contextual bandit algorithms have been recently studied under the federated learning setting to satisfy the demand of keeping data decentralized and pushing the learning of bandit…
IMO: Interactive Multi-Objective Off-Policy Optimization
Nan Wang, Hongning Wang, Maryam Karimzadehgan +2
Most real-world optimization problems have multiple objectives. A system designer needs to find a policy that trades off these objectives to reach a desired operating point. This p…
Learning Neural Contextual Bandits Through Perturbed Rewards
Yiling Jia, Weitong Zhang, Dongruo Zhou +2
Thanks to the power of representation learning, neural contextual bandit algorithms demonstrate remarkable performance improvement against their classical counterparts. But because…
Learning the Optimal Recommendation from Explorative Users
Fan Yao, Chuanhao Li, Denis Nekipelov +2
We propose a new problem setting to study the sequential interactions between a recommender system and a user. Instead of assuming the user is omniscient, static, and explicit, as…
Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits
Chuanhao Li, Hongning Wang
Linear contextual bandit is a popular online learning problem. It has been mostly studied in centralized learning settings. With the surging demand of large-scale decentralized mod…
When Are Linear Stochastic Bandits Attackable?
Huazheng Wang, Haifeng Xu, Hongning Wang
We study adversarial attacks on linear stochastic bandits: by manipulating the rewards, an adversary aims to control the behaviour of the bandit algorithm. Perhaps surprisingly, we…
Improve Learning from Crowds via Generative Augmentation
Zhendong Chu, Hongning Wang
Crowdsourcing provides an efficient label collection schema for supervised machine learning. However, to control annotation cost, each instance in the crowdsourced data is typicall…
When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution
Chuanhao Li, Qingyun Wu, Hongning Wang
Collaborative bandit learning, i.e., bandit algorithms that utilize collaborative filtering techniques to improve sample efficiency in online interactive recommendation, has attrac…