Harness Scaling for Generalizable Agentic Reinforcement Learning Paper • 2610.29458 • Published 27 days ago • 17
Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards Paper • 2610.16533 • Published Oct 12 • 11
ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents Paper • 2610.13395 • Published Oct 9 • 46
Agent-Editing World Model Collection Resources for Agent-Editing World Model (AEWM), a world model for improving long-horizon LLM agents through decision-effect modeling and state rev • 3 items • Updated Sep 25 • 1