Agent Intelligence-Lab 🦞

non-profit

AI & ML interests

LLM, VLM, Agents, Robotics, Physical World

Recent Activity

zli12321 authored a paper about 22 hours ago

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

zli12321 authored a paper about 22 hours ago

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

zli12321 authored a paper about 22 hours ago

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

View all activity

models 7

IntelligenceLab/COS-PLAY

Reinforcement Learning • Updated Apr 24 • 3

IntelligenceLab/Loras

IntelligenceLab/saber-attack-agent-constraint-violation

Robotics • Updated Apr 7 • 9 • 2

IntelligenceLab/saber-attack-agent-action-inflation

Robotics • Updated Apr 7 • 15 • 1

IntelligenceLab/saber-attack-agent-task-failure

Robotics • Updated Apr 7 • 14 • 1

IntelligenceLab/MM-Zero-Logs

Reinforcement Learning • Updated Mar 10 • 1

IntelligenceLab/RewardPreferenceBert

Updated Jun 20, 2025 • 110 • 3

datasets 5

IntelligenceLab/Long-Horizon-Terminal-Bench

Viewer • Updated 2 days ago • 46 • 1.26k • 117

IntelligenceLab/LHTB-leaderboard

Updated 13 days ago • 30

IntelligenceLab/ComfyAgent-David

Viewer • Updated Apr 30 • 350 • 114

IntelligenceLab/Cos-Play-Cold-Start

Viewer • Updated Apr 24 • 69.7k • 141 • 4

IntelligenceLab/VideoHallu

Viewer • Updated Jun 4, 2025 • 3.23k • 1.7k • 5