De Wang, Peng Qi · 2026 · arXiv
DOI: 10.48550/arXiv.2610.27465 · open-access PDF
代理平台正在开始改进自己的代理人:他们阅读部署代理人的执行痕迹,产生一个变化,有一个自动验证器批准它,并在没有人类作者的情况下释放它. 这个循环的多少可以安全地运行没有人类? 我们建议一个平台可以测量两个数量。 验证强度 $σ$是可用的验证器 - 通常是一个LLM法官 - 同意一个可信的参考验证器; 它限制了一个步骤可以改善代理人多少。 可恢复性是如何便宜地取消一个坏的变化:是否取消它需要一个新的验证器的批准,以及多少 t
Machine translation (Meta M2M100); the English original follows.
Agent platforms are starting to improve their own agents: they read a deployed agent's execution traces, derive a change, have an automated verifier approve it, and release it with no human author. How much of this loop can safely run without a human? We propose two quantities a platform can measure. Verifier strength $σ$ is how well the available verifier -- often an LLM judge -- agrees with a trusted reference verifier; it limits how much a step can improve the agent. Recoverability is how cheaply a bad change can be undone: whether undoing it needs a new verifier approval, and how much of t
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27465, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange