# Symbolic-Vector Attention Fusion for Collective Intelligence

arXiv: https://arxiv.org/abs/2604.03955 · HTML: https://mlsanity.com/paper/2604.03955/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Closed-form Continuous-time Neural Models](https://mlsanity.com/paper/2106.13898/) (2021)
- [Attention Residuals](https://mlsanity.com/paper/2603.15031/) (2026)
- [EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery](https://mlsanity.com/paper/2603.08127/) (2026)
- [Toward Reliable Evaluation of LLM-Based Financial Multi-Agent Systems: Taxonomy, Coordination Primacy, and Cost Awareness](https://mlsanity.com/paper/2603.27539/) (2026)
- [An Empirical Study of Multi-Agent Collaboration for Automated Research](https://mlsanity.com/paper/2603.29632/) (2026)
- [CASCADE: Cascaded Scoped Communication for Multi-Agent Re-planning in Disrupted Industrial Environments](https://mlsanity.com/paper/2604.00451/) (2026)

## Built on by (most cited first, 3 of 3)

- [MeloTune: On-Device Arousal Learning and Peer-to-Peer Mood Coupling for Proactive Music Curation](https://mlsanity.com/paper/2604.10815/) (2026)
- [Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems](https://mlsanity.com/paper/2604.19540/) (2026)
- [On the Necessity of a Liquid Substrate for Mesh Intelligence](https://mlsanity.com/paper/2606.28413/) (2026)

## Abstract (arXiv)

When autonomous agents observe different domains of a shared environment, each signal they exchange mixes relevant and irrelevant dimensions. No existing mechanism lets the receiver evaluate which dimensions to absorb. We introduce Symbolic-Vector Attention Fusion (SVAF), the content-evaluation half of a two-level coupling engine for collective intelligence. SVAF decomposes each inter-agent signal into 7 typed semantic fields, evaluates each through a learned fusion gate, and produces a remix -- new knowledge from the intersection of two domains. A band-pass model yields four outcomes (redundant, aligned, guarded, rejected), solving both selectivity and redundancy. The fusion gate independently discovers a cross-domain relevance hierarchy: mood emerges as the highest-weight field by epoch 1, before accuracy plateaus -- consistent with independent mechanistic evidence that LLM emotion representations are structurally embedded along valence-arousal axes. SVAF forms Layer 4 of the Mesh Memory Protocol (MMP); the other half of the coupling engine is a per-agent Closed-form Continuous-time (CfC) neural network at Layer 6, whose learned per-neuron time constants (tau) create the temporal dynamics from which collective intelligence emerges: fast neurons synchronise affect across agents in seconds, while slow neurons preserve domain expertise indefinitely. SVAF determines what enters each agent's cognitive state; CfC determines how that state evolves. Trained on 237K samples from 273 narrative scenarios, SVAF achieves 78.7% three-class accuracy. We verify the complete mesh cognition loop -- from per-field evaluation through remix, CfC state evolution, tau-modulated peer blending, and autonomous action -- in a live deployment with 7 nodes across macOS, iOS, and web.