Tagged articles
2 articles
Page 1 of 1
Machine Heart
Machine Heart
Jun 1, 2026 · Artificial Intelligence

How Galaxea’s Self‑Regressive G0.5 Model Sweeps Seven Embodied Benchmarks

Galaxea’s new G0.5 model outperforms the previous π0.5 baseline on seven diverse embodied‑AI benchmarks by leveraging a unified self‑regressive transformer that jointly generates reasoning and action tokens, achieving large gains in zero‑shot transfer, real‑robot fine‑tuning, simulation, and long‑horizon tasks.

Action CodecEmbodied AINative CoT
0 likes · 13 min read
How Galaxea’s Self‑Regressive G0.5 Model Sweeps Seven Embodied Benchmarks
PaperAgent
PaperAgent
May 2, 2026 · Artificial Intelligence

Can Harnesses Self‑Evolve? Fudan & Peking University’s Agentic Harness Engineering Breakthrough

The paper introduces Agentic Harness Engineering (AHE), showing that a 10‑round evolution improves Coding Agent pass@1 from 69.7% to 77.0% on Terminal‑Bench 2—outperforming Codex‑CLI—and that the evolved harness transfers zero‑shot to SWE‑bench and multiple model families, thanks to three observability pillars.

Ablation StudyBenchmarkCoding Agent
0 likes · 11 min read
Can Harnesses Self‑Evolve? Fudan & Peking University’s Agentic Harness Engineering Breakthrough