Memory-TCG：RRR 记忆整合在智能体对话中解释了什么、没解释什么
When Agents Need to Consolidate Memories: What RRR Consolidation Explains, and What It Does Not Explain, in Conversation ESAA
AI 导读
一项工程研究提出受 RRR（ringing、resonance、renormalization）启发的 Conversation ESAA 扩展 Memory-TCG，并用 480 条事实、三种输出预算比较时序检索、两个简化基线与完整 RRR。
正文 · 原文
Abstract:Language-model agents can share conversational history across sessions, but persistence does not guarantee retrieval of current decisions and their provenance. This engineering study presents Memory-TCG, a Conversation ESAA extension inspired by ringing, resonance and renormalization (RRR), and an exploratory synthetic evaluation comparing chronological retrieval, two simplified baselines (B, recency-aware, and B', authority-aware), full RRR, and variants under three output budgets. With 480 facts and 1,024 tokens, full RRR recalled 0.44 of current decisions, versus 0.06 for chronological retrieval and 0.58 for the oracle ceiling; with 4,096 tokens it recalled all of them. B' and the no-resonance variant matched full RRR in decision recall across all nine scale-budget combinations, as expected when the active decision set and the adapter ordering are the same. The isolated contribution of ringing to decisions was not measured: comparator D1 cuts facts before the graph is built, and the product retains active decisions by rule. Before the output limit, full-RRR conflict F1 was 0.615 at all three scales; after it, at 480 facts and 1,024 tokens, it was 0.000. Reserving 20% of the budget for conflicts raised that F1 to 0.431 in that scenario, at the cost of lowering decision recall from 0.44 to 0.34, and to 0.930 at 4,096 tokens without decision loss. Fixtures are repetitive, comparators are simplified, and the evaluation was not independently replicated; the results support an engineering analysis, not a claim of selectionist superiority.
| Comments: | 8 pages, 4 tables. Code, synthetic data and reproduction instructions: this https URL |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.15644 [cs.SE] |
| (or arXiv:2611.15644v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15644 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Elzo Brito Dos Santos Filho [view email]
[v1]
Wed, 11 Nov 2026 15:55:20 UTC (15 KB)
来源：arXiv cs.AI · arxiv.org