177 citations · 220 across the 22 of their papers we have counts for
22 papers
Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation
Lajanugen Logeswaran, Jaekyeom Kim, Sungryull Sohn +2
We present a scalable pipeline for automatically generating high-quality training data for web agents. In particular, a major challenge in identifying high-quality training instanc…
Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation
Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim +6
Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories inclu…
Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents
Yunseok Jang, Yeda Song, Sungryull Sohn +5
Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have sparked significant interest in developing GUI visual agents. We introduce MONDAY (Mobile…
Do Not Trust Licenses You See: Dataset Compliance Requires Massive-Scale AI-Powered Lifecycle Tracing
Jaekyeom Kim, Sungryull Sohn, Gerrard Jeongwon Jo +5
This paper argues that a dataset's legal risk cannot be accurately assessed by its license terms alone; instead, tracking dataset redistribution and its full lifecycle is essential…
Interactive and Expressive Code-Augmented Planning with Large Language Models
Anthony Z. Liu, Xinhe Wang, Jacob Sansom +5
Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. R…
Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents
Jaekyeom Kim, Dong-Ki Kim, Lajanugen Logeswaran +2
In this paper, we introduce Auto-Intent, a method to adapt a pre-trained large language model (LLM) as an agent for a target domain without direct fine-tuning, where we empirically…
AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
Yao Fu, Dong-Ki Kim, Jaekyeom Kim +4
Recent advances in large language models (LLMs) have empowered AI agents capable of performing various sequential decision-making tasks. However, effectively guiding LLMs to perfor…
TOD-Flow: Modeling the Structure of Task-Oriented Dialogues
Sungryull Sohn, Yiwei Lyu, Anthony Liu +4
Task-Oriented Dialogue (TOD) systems have become crucial components in interactive artificial intelligence applications. While recent advances have capitalized on pre-trained langu…
Code Models are Zero-shot Precondition Reasoners
Lajanugen Logeswaran, Sungryull Sohn, Yiwei Lyu +5
One of the fundamental skills required for an agent acting in an environment to complete tasks is the ability to understand what actions are plausible at any given point. This work…
MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning
Dong-Ki Kim, Sungryull Sohn, Lajanugen Logeswaran +2
Recently, there has been an increasing interest in automated prompt optimization based on reinforcement learning (RL). This approach offers important advantages, such as generating…
From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning
Zheyuan Zhang, Shane Storks, Fengyuan Hu +4
Pre-trained language models (PLMs) have shown impressive performance in various language tasks. However, they are prone to spurious correlations, and often generate illusory inform…
A Picture is Worth a Thousand Words: Language Models Plan from Pixels
Anthony Z. Liu, Lajanugen Logeswaran, Sungryull Sohn +1
Planning is an important capability of artificial agents that perform long-horizon tasks in real-world environments. In this work, we explore the use of pre-trained language models…
Multimodal Subtask Graph Generation from Instructional Videos
Yunseok Jang, Sungryull Sohn, Lajanugen Logeswaran +3
Real-world tasks consist of multiple inter-dependent subtasks (e.g., a dirty pan needs to be washed before it can be used for cooking). In this work, we aim to model the causal dep…
Unsupervised Task Graph Generation from Instructional Video Transcripts
Lajanugen Logeswaran, Sungryull Sohn, Yunseok Jang +2
This work explores the problem of generating task graphs of real-world activities. Different from prior formulations, we consider a setting where text transcripts of instructional…
Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization
Sungryull Sohn, Hyunjae Woo, Jongwook Choi +4
We tackle real-world problems with complex structures beyond the pixel-based game or simulator. We formulate it as a few-shot reinforcement learning problem where a task is charact…
Learning Parameterized Task Structure for Generalization to Unseen Entities
Anthony Z. Liu, Sungryull Sohn, Mahdi Qazwini +1
Real world tasks are hierarchical and compositional. Tasks can be composed of multiple subtasks (or sub-goals) that are dependent on each other. These subtasks are defined in terms…
Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning
Christopher Hoang, Sungryull Sohn, Jongwook Choi +2
Operating in the real-world often requires agents to learn about a complex environment and apply this understanding to achieve a breadth of goals. This problem, known as goal-condi…
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
Sungryull Sohn, Sungtae Lee, Jongwook Choi +3
We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agent's trajectory that improves the sample efficiency in sparse-reward MDPs. We show that any optimal p…
Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment
Wilka Carvalho, Anthony Liang, Kimin Lee +4
First-person object-interaction tasks in high-fidelity, 3D, simulated environments such as the AI2Thor virtual home-environment pose significant sample-efficiency challenges for re…
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
Sungryull Sohn, Hyunjae Woo, Jongwook Choi +1
We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph which describes a set of subtasks and their dependencies that are unknown to th…
Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies
Sungryull Sohn, Junhyuk Oh, Honglak Lee
We introduce a new RL problem where the agent is required to generalize to a previously-unseen environment characterized by a subtask graph which describes a set of subtasks and th…
Learning to Generate Long-term Future via Hierarchical Prediction
Ruben Villegas, Jimei Yang, Yuliang Zou +3
We propose a hierarchical approach for making long-term predictions of future frames. To avoid inherent compounding errors in recursive pixel-level prediction, we propose to first…