Multiscale Policy Optimization for Long-Horizon LLM Agents Paper • 2610.35013 • Published 3 days ago • 113
Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination Paper • 2610.33503 • Published 5 days ago • 13
PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination Paper • 2605.03571 • Published May 5 • 6
InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation? Paper • 2604.27419 • Published Apr 30 • 12
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration Paper • 2603.29557 • Published Mar 31 • 15