From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement Paper • 2607.23802 • Published 17 days ago • 105
Agents-A1 Collection Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. • 12 items • Updated 26 days ago • 40
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation Paper • 2607.05147 • Published Jul 6 • 41
Laguna XS 2.1 Collection Designed for agentic coding and long-horizon work on a local machine. Licensed under OpenMDW-1.1. • 9 items • Updated Jul 2 • 24
Tmax Collection Data and models associated with "Tmax: A simple recipe for terminal agents". paper: https://arxiv.org/abs/2606.23321 • 23 items • Updated Jun 23 • 19