# Контекст решения: Постоянное поведенческое обучение для AI-агентов

> Полный текст доступен на английском

**Published:** 9 ноября 2026 г.
**Author:** Nima Vahdat, Pashootan Vaezipoor
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/articles/decision-context-persistent-behavioral-learning-for-ai-agents

arXiv:2611.08644v1 Тип объявления: новый Абстракт: LLM-агенты не учатся на исправлениях между сессиями. Пользователь исправляет одну и ту же ошибку в начале каждого разговора. Существующие системы памяти агентов в основном работают с фактами, такими как предпочтения, сущности и разговорные…

arXiv:2611.08644v1 Announce Type: new Abstract: LLM agents do not learn from corrections across sessions. A user fixes the same mistake at the start of every conversation. Existing agent memory systems primarily handle facts, such as preferences, entities, and conversational history, rather than procedural knowledge. We present Forge Decision Context (forge_dc), a system that captures behavioral signals from human corrections and self-assessed tool-call failures, compiles them into imperative RULE directives, and injects them at the decision points where they apply. We evaluate forge_dc alongside four predecessor approaches on DC-Bench, a new benchmark of 71 scenarios across nine behavioral dimensions, built from real executed agent traces in a deterministic mocked-tool environment. forge_dc reaches 95% compliance, up from 55% with naive retrieval, while injecting approximately 10 times fewer tokens per query. Across the five-stage progression, the strongest systems represent behavioral memory as explicit directives and deliver it at the decision points where it applies. The results identify representation, activation, and placement as central design choices for persistent behavioral learning.

---

*Материал агрегирован из первоисточника: [arXiv — cs.AI](https://arxiv.org/abs/2611.08644). Открыть оригинал.*

**Теги:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*