AgentGym

AI & ML interests

LLM Agent

Recent Activity

KYLN24 authored a paper about 1 month ago

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

KYLN24 submitted a paper about 1 month ago

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

WooooDyy authored a paper 5 months ago

AI Can Learn Scientific Taste

View all activity

authored a paper about 1 month ago

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

Paper • 2606.24526 • Published Jun 23 • 5

submitted a paper to Daily Papers about 1 month ago

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

Paper • 2606.24526 • Published Jun 23 • 5

authored 2 papers 5 months ago

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published Mar 15 • 432

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents

Paper • 2602.12984 • Published Feb 13 • 7

authored a paper 6 months ago

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

Paper • 2601.11077 • Published Jan 16 • 67

authored a paper 6 months ago

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development

Paper • 2601.11077 • Published Jan 16 • 67

authored a paper 7 months ago

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding

Paper • 2601.10343 • Published Jan 15 • 2

authored 4 papers 8 months ago

Memory in the Age of AI Agents

Paper • 2512.13564 • Published Dec 15, 2025 • 160

Better Process Supervision with Bi-directional Rewarding Signals

Paper • 2503.04618 • Published Mar 6, 2025

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

Paper • 2509.08755 • Published Sep 10, 2025 • 56

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

Paper • 2510.18927 • Published Oct 21, 2025 • 86

authored a paper 8 months ago

Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction

Paper • 2512.04987 • Published Dec 4, 2025 • 85

authored a paper 8 months ago

Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction

Paper • 2512.04987 • Published Dec 4, 2025 • 85

in AgentGym/AgentGym-RL-Data-ID 11 months ago

Upload webarena_train.json

#3 opened 11 months ago by

Add comprehensive dataset card for AgentGym-RL-Data-ID

#2 opened 11 months ago by

published a dataset 11 months ago

AgentGym/AgentGym-RL-Data-ID

Viewer • Updated Sep 12, 2025 • 186k • 224 • 7

authored 2 papers 11 months ago

Pre-Trained Policy Discriminators are General Reward Models

Paper • 2507.05197 • Published Jul 7, 2025 • 39

BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset

Paper • 2507.03483 • Published Jul 4, 2025 • 24

in AgentGym/AgentTraj-L 11 months ago

Update sciworld_train.json

#3 opened 11 months ago by

updated a dataset 11 months ago

AgentGym/AgentGym-RL-Data-ID

Viewer • Updated Sep 12, 2025 • 186k • 224 • 7