# 决策语境：AI智能体的持久行为学习

> 全文为英语

**Published:** 2026年11月9日
**Author:** Nima Vahdat, Pashootan Vaezipoor
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/decision-context-persistent-behavioral-learning-for-ai-agents

arXiv:2611.08644v1 通告类型：新 摘要：LLM智能体无法从跨会话的纠正中学习。用户在每次对话开始时都要修正同一个错误。现有的智能体记忆系统主要处理事实，如偏好、实体和对话…

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.

---

*内容来自原始来源： [arXiv — cs.AI](https://arxiv.org/abs/2611.08644). 查看原文.*

**标签：** #arXiv

---

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