43 citations · 53 across the 19 of their papers we have counts for
20 papers
Skill Reuse as Compression in Agentic RL
Zhikun Xu, Yu Feng, Jacob Dineen +3
Large language model agents trained with reinforcement learning (RL) often learn brittle, task-specific shortcuts. We hypothesize that agents generalize better when their successfu…
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
Xuwei Ding, Skylar Zhai, Linxin Song +6
Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatic…
Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks
Yuqing Yang, Tengxiao Liu, Wang Bill Zhu +3
As LLM-based assistants become persistent and personalized, they must extract and retain useful information from past conversations as memory. However, the types of information wor…
Video-Based Reward Modeling for Computer-Use Agents
Linxin Song, Jieyu Zhang, Huanxin Sheng +6
Computer-using agents (CUAs) are becoming increasingly capable; however, it remains difficult to scale evaluation of whether a trajectory truly fulfills a user instruction. In this…
DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning
Fangyuan Xu, Sihao Chen, Zinan Lin +13
Differentially private (DP) synthetic data generation plays a pivotal role in developing large language models (LLMs) on private data, where data owners cannot provide eyes-on acce…
Experiential Reinforcement Learning
Taiwei Shi, Sihao Chen, Bowen Jiang +3
Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually…
One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence
Bowen Jiang, Taiwei Shi, Ryo Kamoi +5
This paper introduces OMAR: One Model, All Roles, a reinforcement learning framework that enables AI to develop social intelligence through multi-turn, multi-agent conversational s…
CoAct-1: Computer-using Multi-Agent System with Coding Actions
Linxin Song, Yutong Dai, Viraj Prabhu +9
Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks. While augmenting these…
STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models
Kai Chen, Zihao He, Taiwei Shi +1
Steerability, or the ability of large language models (LLMs) to adapt outputs to align with diverse community-specific norms, perspectives, and communication styles, is critical fo…
The Hallucination Tax of Reinforcement Finetuning
Linxin Song, Taiwei Shi, Jieyu Zhao
Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs). However, its impact on model trustworthiness…
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
Taiwei Shi, Yiyang Wu, Linxin Song +2
Reinforcement finetuning (RFT) has shown great potential for enhancing the mathematical reasoning capabilities of large language models (LLMs), but it is often sample- and compute-…
Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
Linxin Song, Xuwei Ding, Jieyu Zhang +6
Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Und…
On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
Yue Huang, Chujie Gao, Siyuan Wu +63
Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions.…
Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation
Yijun Pan, Taiwei Shi, Jieyu Zhao +1
Large language models (LLMs) are highly sensitive to even small amounts of unsafe training data, making effective detection and filtering essential for trustworthy model developmen…
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
Taiwei Shi, Zhuoer Wang, Longqi Yang +12
As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on hum…
How Susceptible are Large Language Models to Ideological Manipulation?
Kai Chen, Zihao He, Jun Yan +2
Large Language Models (LLMs) possess the potential to exert substantial influence on public perceptions and interactions with information. This raises concerns about the societal i…
Can Language Model Moderators Improve the Health of Online Discourse?
Hyundong Cho, Shuai Liu, Taiwei Shi +8
Conversational moderation of online communities is crucial to maintaining civility for a constructive environment, but it is challenging to scale and harmful to moderators. The inc…
Safer-Instruct: Aligning Language Models with Automated Preference Data
Taiwei Shi, Kai Chen, Jieyu Zhao
Reinforcement learning from human feedback (RLHF) is a vital strategy for enhancing model capability in language models. However, annotating preference data for RLHF is a resource-…
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
Minzhi Li, Taiwei Shi, Caleb Ziems +4
Annotated data plays a critical role in Natural Language Processing (NLP) in training models and evaluating their performance. Given recent developments in Large Language Models (L…
Neural Story Planning
Anbang Ye, Christopher Cui, Taiwei Shi +1
Automated plot generation is the challenge of generating a sequence of events that will be perceived by readers as the plot of a coherent story. Traditional symbolic planners plan…