AgentRewardBench - a McGill-NLP Collection

McGill-NLP 's Collections

The Markovian Thinker

INJONGO

Unequal unlearning

AgentRewardBench

CHASE

LLM2Vec

WebLINX

AURORA

Statcan Dialogue Dataset & Models

AgentRewardBench

updated Apr 15, 2025

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories

Paper • 2504.08942 • Published Apr 11, 2025 • 28
McGill-NLP/agent-reward-bench

Viewer • Updated Apr 21, 2025 • 1.41k • 4.49k • 4
Running

4

Agent Reward Bench Demo

💻

4

Explore agent trajectories and judgments in web benchmarks
Runtime error

3

Agent Reward Bench Leaderboard

🥇

3

Leaderboard for AgentRewardBench