Заголовок на английскомMore Rules, Longer Lists? Benchmarking Self-Evolving Agents on a Hidden-Rule Curriculum
arXiv:2610.40758v1 Announce Type: new Abstract: Self-evolving agents rewrite a persistent state from feedback, but it is largely untested whether this lets them learn a rule nobody told them. An agent can also pass by writing down each correction as an exception, and its list…
Кратко от AI: Главные тезисы
- arXiv:2610.40758v1 Announce Type: new Abstract: Self-evolving agents rewrite a persistent state from feedback, but it is largely untested whether this lets them learn a rule nobody told them
- An agent can also pass by writing down each correction as an exception, and its list…
More Rules, Longer Lists? Benchmarking Self-Evolving Agents on a Hidden-Rule Curriculum
Похожие материалы
Самые интересные ИИ-инструменты и новости за прошедшую неделю
📌 Самые интересные ИИ-инструменты и новости за прошедшую неделю GPT-6.1 Terra — новая модель OpenAI для управления компьютером, программирования и работы с документами. Genie 4 — нейросеть Google, создающая интерактивные виртуальные миры по текстовому описанию. Gemini 4 Carbon…
NVIDIA выпустила Nemotron 3.5 Bolt E4B
🌟 NVIDIA выпустила Nemotron 3.5 Bolt E4B Спустя чуть больше недели после релиза, когда вместе с мультимодальной Nemotron 3.5 Super VL вышла её сжатая версия Bolt на 74 млрд параметров, NVIDIA, как и обещала, опубликовала веса совсем компактной модели для периферийных устройств.…
ENCircumventing the Computational Hardness of Computational Arbitrage
arXiv:2610.40831v1 Announce Type: new Abstract: AI model marketplaces host providers with heterogeneous costs and capabilities. These differences create an opportunity for computational arbitrage (Olmedo et al., 2026), in which an intermediary purchases inference from a…
ENBeyond Plausible Prediction: Safety Sufficiency in Web World Models
arXiv:2610.40798v1 Announce Type: new Abstract: Web world models increasingly predict the consequences of candidate actions before agents act, yet a plausible predicted future does not necessarily support the correct safety decision. In a matched human evaluation of 3,000…