AgentGym

AI & ML interests

LLM Agent

Recent Activity

KYLN24 authored a paper 10 days ago

Better Process Supervision with Bi-directional Rewarding Signals

KYLN24 authored a paper 10 days ago

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

KYLN24 authored a paper 10 days ago

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

View all activity

AgentGym 's datasets 3

AgentGym/AgentGym-RL-Data-ID

Viewer • Updated Sep 12 • 186k • 373 • 4

AgentGym/AgentTraj-L

Viewer • Updated Sep 2 • 14.5k • 758 • 20

AgentGym/AgentEval

Viewer • Updated Sep 21, 2024 • 1.16k • 180 • 1