Metraipolis › archive › dc_ea993b87c2c9
An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency — arXiv:2609.22043
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22043
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:27:49.911Z
- SHA-256 of the archived text
ab797bbcaba147373c5dbba56ac58f83171f8e6129674e62fc85b7a8b7e946b1- Stable URL of this page
https://metraipolis.com/documento/dc_ea993b87c2c9
How to cite
An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency — arXiv:2609.22043 — arXiv (en), https://arxiv.org/abs/2609.22043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea993b87c2c9 (Metraipolis archive dc_ea993b87c2c9, sha256 ab797bbcaba147373c5dbba56ac58f83171f8e6129674e62fc85b7a8b7e946b1)
BibTeX
@misc{dcea993b87c2c9,
title = {An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency — arXiv:2609.22043},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22043},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea993b87c2c9; sha256 ab797bbcaba147373c5dbba56ac58f83171f8e6129674e62fc85b7a8b7e946b1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Memory systems for large language models have focused predominantly on efficient retrieval, whereas the decision of whether retrieved memories should be trusted has received comparatively little attention. When the memory store contains conflicting positions, standard retrieval-augmented generation (RAG) blindly injects memories and amplifies hallucinations: in models susceptible to memory injection, the RAG hallucination rate under conflicting memories is markedly higher than that of a memory-free baseline. Inspired by memory signaling mechanisms in the prefrontal cortex, we propose the Memory Decision Layer (MDL), a zero-parameter memory decision controller situated between the retrieval and generation stages. Its core is a three-signal complementary encoder that fuses relevance, reliability, and task risk through QR-based orthogonal subspace projection and a meta-working-memory signal into an interpretable decision representation that quantifies the trustworthiness of retrieved memories. Building on this encoder, MDL explicitly decouples confidence from consistency and introduces risk inversion and explicit abstention. Evaluations on mainstream large language models and multiple open-source datasets show that MDL reduces the hallucination rate under conflicting memories by about 56.04% in general scenarios and approaches zero hallucination in high-risk scenarios. The controller is fully white-box: it relies purely on geometric operations, requires no trained parameters, and adds only about 0.14 ms per decision -- roughly 50x faster than the embedding-retrieval step that precedes it and four to five orders of magnitude faster than an LLM self-evaluation call. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.22043 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T01:00:30.309Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).