163 citations · 216 across the 21 of their papers we have counts for
22 papers
CUAWright: A Minimal Unified Interface for Digital Agents
Yadong Lu, Theodore Lee, Yifei Li +5
The prevailing approach to computer-use agents couples a model with a domain-specific harness: a browser or desktop environment equipped with human engineered tools that are fixed…
Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
Yash Pandya, Sahil Gupta, Sarthak Harne +10
Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset. The applications that matter most are login-gated and s…
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…
ECHO: Terminal Agents Learn World Models for Free
Vaishnavi Shrivastava, Piero Kauffmann, Ahmed Awadallah +1
CLI agents are the closest thing language models have to an embodied setting: the model emits commands, the terminal executes them, and the returned stream -- stdout, errors, files…
MEMENTO: Teaching LLMs to Manage Their Own Context
Vasilis Kontonis, Yuchen Zeng, Shivam Garg +7
Reasoning models think in long, unstructured streams with no mechanism for compressing or organizing their own intermediate state. We introduce MEMENTO: a method that teaches model…
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…
Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces
Karan Gupta, Pranav Vajreshwari, Yash Pandya +3
Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these cha…
Beyond Clicking:A Step Towards Generalist GUI Grounding via Text Dragging
Zeyi Liao, Yadong Lu, Boyu Gou +2
Graphical user interface (GUI) grounding, the process of mapping human instructions to GUI actions, serves as a fundamental basis to autonomous GUI agents. While existing grounding…
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…
Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
Vaishnavi Shrivastava, Ahmed Awadallah, Vidhisha Balachandran +3
Large language models trained with reinforcement learning with verifiable rewards tend to trade accuracy for length--inflating response lengths to achieve gains in accuracy. While…
Phi-4-reasoning Technical Report
Marah Abdin, Sahaj Agarwal, Ahmed Awadallah +20
We introduce Phi-4-reasoning, a 14-billion parameter reasoning model that achieves strong performance on complex reasoning tasks. Trained via supervised fine-tuning of Phi-4 on car…
Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
Vardaan Pahuja, Yadong Lu, Corby Rosset +5
Recent success in large multimodal models (LMMs) has sparked promising applications of agents capable of autonomously completing complex web tasks. While open-source LMM agents hav…
OmniParser for Pure Vision Based GUI Agent
Yadong Lu, Jianwei Yang, Yelong Shen +1
The recent success of large vision language models shows great potential in driving the agent system operating on user interfaces. However, we argue that the power multimodal model…
AgentInstruct: Toward Generative Teaching with Agentic Flows
Arindam Mitra, Luciano Del Corro, Guoqing Zheng +11
Synthetic data is becoming increasingly important for accelerating the development of language models, both large and small. Despite several successful use cases, researchers also…
sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting
Sanchit Ahuja, Kumar Tanmay, Hardik Hansrajbhai Chauhan +9
Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel app…
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy +3
Reinforcement learning from human feedback (RLHF) has emerged as a central tool for language model alignment. We consider online exploration in RLHF, which exploits interactive acc…
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Corby Rosset, Ching-An Cheng, Arindam Mitra +3
This paper studies post-training large language models (LLMs) using preference feedback from a powerful oracle to help a model iteratively improve over itself. The typical approach…
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Marah Abdin, Jyoti Aneja, Hany Awadalla +126
We introduce phi-3-mini, a 3.8 billion parameter language model trained on 3.3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal test…
Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents
Corby Rosset, Ho-Lam Chung, Guanghui Qin +5
Existing question answering (QA) datasets are no longer challenging to most powerful Large Language Models (LLMs). Traditional QA benchmarks like TriviaQA, NaturalQuestions, ELI5 a…
Orca-Math: Unlocking the potential of SLMs in Grade School Math
Arindam Mitra, Hamed Khanpour, Corby Rosset +1
Mathematical word problem-solving has long been recognized as a complex task for small language models (SLMs). A recent study hypothesized that the smallest model size, needed to a…
Axiomatic Preference Modeling for Longform Question Answering
Corby Rosset, Guoqing Zheng, Victor Dibia +2
The remarkable abilities of large language models (LLMs) like GPT-4 partially stem from post-training processes like Reinforcement Learning from Human Feedback (RLHF) involving hum…
Orca 2: Teaching Small Language Models How to Reason
Arindam Mitra, Luciano Del Corro, Shweti Mahajan +12
Orca 1 learns from rich signals, such as explanation traces, allowing it to outperform conventional instruction-tuned models on benchmarks like BigBench Hard and AGIEval. In Orca 2…