Newest papers

Recoverability and Verifier Strength: Two Measured Preconditions for Unattended Agent Self-Improvement

De Wang, Peng Qi · 2026 · arXiv

DOI: 10.48550/arXiv.2610.27465 · open-access PDF

Arabic

وتبدأ منصات الممثلين في تحسين الممثلين الخاصة بهم: إنهم يقرأون أساليب تنفيذ الممثل المستخدم، وتتلقى تغييرات، وتتلقى مؤشرًا تلقائيًا، وتتلقى ذلك بدون مؤشر بشري. كم من هذه الخطوط يمكن أن تعمل آمنًا بدون إنسان؟ ونحن نقترح كمية اثنين من منصة يمكن قياسها. قوة المؤشر $σ$ هو ما هو جيد الممثل المتوفر - غالبًا ما يكون محاكما LLM - يتفق مع مؤشر المراجعة الموثوق به؛ فإنه يحدد كم خطوة يمكن تحسين الممثل.

Machine translation (Meta M2M100); the English original follows.

Abstract

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange