Meta-Harness: Can harness engineering code self-iterate? A Stanford paper analysis
Meta-Harness | Harness工程代码能自我迭代吗 | 斯坦福论文 | 文本优化方法的缺陷 | coding agent | 提议器 | 搜索循环 | 局限性 | 交给AI
Stanford, MIT, and KRAFTON AI present Meta-Harness, which turns harness optimization into an outer-loop search and beats manual or text-optimization baselines on 3 task types. The system uses a coding agent to inspect filesystem history; after 10 search iterations, the data exceeds 10 million tokens, and on online text classification it matched OPRO’s 60-iteration result in 4 iterations while reaching 75.9% average accuracy on 5 OOD datasets. The key point is full-feedback retention rather than compression; the paper also reports about 20 TerminalBench-2 iterations at a total cost of a few hundred dollars.
Why it matters: This is a good research-release explainer for agent builders: the mechanism is clear and the post includes concrete numbers, so HKR-H/K/R all pass. It stays at 80 because the source is a secondary YouTube summary, not the primary paper or official release, and the impact is still