複雜的智能體記憶是否總是必要？樸素 RAG 比我們想像的更強
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
研究發現，在多項對話記憶基準測試中，直接檢索原始對話歷史的 Raw-RAG 整體表現勝過複雜的智能體記憶系統。Raw-RAG 在七種基準測試與模型設定中的六種排名第一，較最強的受測智能體記憶系統高 0.13–5.53 分。結果顯示，保留原始證據有助提升必要資訊的覆蓋率，樸素 RAG 是評估對話記憶系統的重要基線。
Published on Oct 22
Authors:
,
,
,
,
Abstract
Raw retrieval-augmented generation over unprocessed conversation history outperforms complex agentic memory systems across multiple benchmarks, indicating that preserving raw evidence is more critical than elaborate memory transformations.
LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other complex operations. Is this complexity always necessary? We study Raw-RAG, a naive RAG baseline using dense retrieval and reranking over raw history to supply evidence to a reader LLM. Across LoCoMo, LongMemEval, MEME, and MemoryAgentBench, Raw-RAG ranks first among the compared memory systems in six of seven benchmark-model settings, outperforming the strongest compared agentic memory system by 0.13-5.53 points. We investigate why raw-history retrieval remains competitive. Evidence analysis shows that its higher coverage of necessary evidence can offset lower utilization. Useful evidence includes both answer values and the relations and dependency paths needed to derive them. Even complete access to transformed memory stores leaves an accuracy gap relative to raw evidence, highlighting the importance of preserving raw information. These findings challenge the necessity of complex agentic memory for the evaluated conversation tasks and establish naive RAG as an essential baseline.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.30755
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.30755 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.30755 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.30755 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源：HuggingFace Daily Papers（社區熱門論文） · huggingface.co