16 citations · 29 across the 25 of their papers we have counts for
28 papers
Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents
Yiran Wu, Andrew Zhao, Yurui Chang +2
Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary rewards fail to distinguish…
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Bo Liu, Simon Yu, Yiding Jiang +15
Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, stat…
Mitigating Over-Personalization in LLMs via Structured Memory
Hakeem Hannoon, Andrew Zhao, Mihir Narayan +2
Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions. However, when stored user information is reintroduced into the…
Shieldstral
Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7 its size on text safety benchmarks and set…
Fara-1.5: Scalable Learning Environments for Computer Use Agents
Ahmed Awadallah, Sahil Gupta, Yash Lara +12
Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies. This requires two key ingredients: environment…
Voxtral TTS
Mistral-AI, :, Alexander H. Liu +186
We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid…
The Art of Building Verifiers for Computer Use Agents
Corby Rosset, Pratyusha Sharma, Andrew Zhao +2
Verifying the success of computer use agent (CUA) trajectories is a critical challenge: without reliable verification, neither evaluation nor training signal can be trusted. In thi…
Bayesian Learning in Episodic Zero-Sum Games
Chang-Wei Yueh, Andy Zhao, Ashutosh Nayyar +1
We study Bayesian learning in episodic, finite-horizon zero-sum Markov games with unknown transition and reward models. We investigate a posterior algorithm in which each player ma…
Fara-7B: An Efficient Agentic Model for Computer Use
Ahmed Awadallah, Yash Lara, Raghav Magazine +9
Progress in computer use agents (CUAs) has been constrained by the absence of large and high-quality datasets that capture how humans interact with a computer. While LLMs have thri…
Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
Andrew Zhao, Reshmi Ghosh, Vitor Carvalho +4
Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on…
Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
Yulin Wang, Yang Yue, Huanqian Wang +11
Human vision is highly adaptive, efficiently sampling intricate environments by sequentially fixating on task-relevant regions. In contrast, prevailing machine vision models passiv…
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
Yiran Wu, Mauricio Velazco, Andrew Zhao +9
We present ExCyTIn-Bench, the first benchmark to Evaluate an LLM agent X on the task of Cyber Threat Investigation through security questions derived from investigation graphs. Rea…
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Shenzhi Wang, Le Yu, Chang Gao +15
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs), while its mechanis…
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Andrew Zhao, Yiran Wu, Yang Yue +7
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rew…
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Yang Yue, Zhiqi Chen, Rui Lu +4
Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated notable success in enhancing the reasoning performance of large language models (LLMs), particularly…
Towards Understanding the Benefit of Multitask Representation Learning in Decision Process
Rui Lu, Yang Yue, Andrew Zhao +2
Multitask Representation Learning (MRL) has emerged as a prevalent technique to improve sample efficiency in Reinforcement Learning (RL). Empirical studies have found that training…
Optimizing Social Media Annotation of HPV Vaccine Skepticism and Misinformation Using Large Language Models: An Experimental Evaluation of In-Context Learning and Fine-Tuning Stance Detection Across Multiple Models
Luhang Sun, Varsha Pendyala, Yun-Shiuan Chuang +6
This paper leverages large-language models (LLMs) to experimentally determine optimal strategies for scaling up social media content annotation for stance detection on HPV vaccine-…
Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey
Matthieu Lin, Jenny Sheng, Andrew Zhao +7
This survey organizes the intricate literature on the design and optimization of emerging structures around post-trained LMs. We refer to this overarching structure as scaffolded L…
Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing
Huanqian Wang, Yang Yue, Rui Lu +5
Large Language Models (LLMs) have demonstrated great potential as generalist assistants, showcasing powerful task understanding and problem-solving capabilities. To deploy LLMs as…
Empowering Interdisciplinary Insights with Dynamic Graph Embedding Trajectories
Yiqiao Jin, Andrew Zhao, Yeon-Chang Lee +3
We developed DyGETViz, a novel framework for effectively visualizing dynamic graphs (DGs) that are ubiquitous across diverse real-world systems. This framework leverages recent adv…
DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints
Andrew Zhao, Quentin Xu, Matthieu Lin +4
Recent advances in large language model assistants have made them indispensable, raising significant concerns over managing their safety. Automated red teaming offers a promising a…
Exploring Text-to-Motion Generation with Human Preference
Jenny Sheng, Matthieu Lin, Andrew Zhao +5
This paper presents an exploration of preference learning in text-to-motion generation. We find that current improvements in text-to-motion generation still rely on datasets requir…
Augmenting Unsupervised Reinforcement Learning with Self-Reference
Andrew Zhao, Erle Zhu, Rui Lu +3
Humans possess the ability to draw on past experiences explicitly when learning new tasks and applying them accordingly. We believe this capacity for self-referencing is especially…
Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation
Shenzhi Wang, Chang Liu, Zilong Zheng +7
Recent breakthroughs in large language models (LLMs) have brought remarkable success in the field of LLM-as-Agent. Nevertheless, a prevalent assumption is that the information proc…