8 citations · 17 across the 14 of their papers we have counts for
7 papers · 1 filter
Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
Junhong Shen, Hao Bai, Lunjun Zhang +8
The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this…
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
Yifei Zhou, Song Jiang, Yuandong Tian +4
Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. However, existing multi-turn RL algorithms for optimizing LLM agents fail to perform…
Digi-Q: Learning Q-Value Functions for Training Device-Control Agents
Hao Bai, Yifei Zhou, Li Erran Li +2
While a number of existing approaches for building foundation model agents rely on prompting or fine-tuning with human demonstrations, it is not sufficient in dynamic environments…
Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
Yifei Zhou, Qianlan Yang, Kaixiang Lin +5
The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advance…
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Hao Bai, Yifei Zhou, Mert Cemri +4
Training corpuses for vision language models (VLMs) typically lack sufficient amounts of decision-centric data. This renders off-the-shelf VLMs sub-optimal for decision-making task…
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
Yifei Zhou, Andrea Zanette, Jiayi Pan +2
A broad use case of large language models (LLMs) is in goal-directed decision-making tasks (or "agent" tasks), where an LLM needs to not just generate completions for a given promp…
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
Yifei Zhou, Ayush Sekhari, Yuda Song +1
Hybrid RL is the setting where an RL agent has access to both offline data and online data by interacting with the real-world environment. In this work, we propose a new hybrid RL…