A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning

• URL: http://arxiv.org/abs/2601.06851v1
• Date: Sun, 11 Jan 2026 10:48:35 GMT
• Title: A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning
• Authors: Pedro Urbina-Rodriguez, Zafeirios Fountas, Fernando E. Rosas, Jun Wang, Andrea I. Luppi, Haitham Bou-Ammar, Murray Shanahan, Pedro A. M. Mediano,
• Abstract summary: We show that large language models spontaneously develop synergistic cores.<n>We find that areas in middle layers exhibit synergistic processing while early and late layers rely on redundancy.<n>This convergence suggests that synergistic information processing is a fundamental property of intelligence.
• Score: 50.68188138112555
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The independent evolution of intelligence in biological and artificial systems offers a unique opportunity to identify its fundamental computational principles. Here we show that large language models spontaneously develop synergistic cores -- components where information integration exceeds individual parts -- remarkably similar to those in the human brain. Using principles of information decomposition across multiple LLM model families and architectures, we find that areas in middle layers exhibit synergistic processing while early and late layers rely on redundancy, mirroring the informational organisation in biological brains. This organisation emerges through learning and is absent in randomly initialised networks. Crucially, ablating synergistic components causes disproportionate behavioural changes and performance loss, aligning with theoretical predictions about the fragility of synergy. Moreover, fine-tuning synergistic regions through reinforcement learning yields significantly greater performance gains than training redundant components, yet supervised fine-tuning shows no such advantage. This convergence suggests that synergistic information processing is a fundamental property of intelligence, providing targets for principled model design and testable predictions for biological intelligence.

Related papers

• Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework [7.582178041791117]
  This paper investigates the implementation of a leading theory of consciousness, Integrated Information Theory (IIT), within language models via a reward-based learning paradigm.<n>We formulate a novel reward function that quantifies a text's causality, coherence and integration, characteristics associated with conscious processing.<n>On out of domain tasks, careful tuning achieves up to a 31% reduction in output length while preserving accuracy levels comparable to the base model.
  arXiv  Detail & Related papers  (2026-01-30T10:07:58Z)
• Lessons from Neuroscience for AI: How integrating Actions, Compositional Structure and Episodic Memory could enable Safe, Interpretable and Human-Like AI [0.8481798330936976]
  We argue that foundation models should integrate actions, at multiple scales of abstraction, with a compositional generative architecture and episodic memory.<n>We describe how the addition of these missing components to foundation models could help address some of their current deficiencies.<n>We conclude by arguing that a rekindling of the historically fruitful exchange of ideas between brain science and AI will help pave the way towards safe and interpretable human-centered AI.
  arXiv  Detail & Related papers  (2025-12-27T11:54:54Z)
• Intelligence Foundation Model: A New Perspective to Approach Artificial General Intelligence [55.07411490538404]
  We propose a new perspective for approaching artificial general intelligence (AGI) through an intelligence foundation model (IFM)<n>IFM aims to acquire the underlying mechanisms of intelligence by learning directly from diverse intelligent behaviors.
  arXiv  Detail & Related papers  (2025-11-13T09:28:41Z)
• A Neural Network Model of Complementary Learning Systems: Pattern Separation and Completion for Continual Learning [2.9123921488295768]
  Learning new information without forgetting prior knowledge is central to human intelligence.<n>In contrast, neural network models suffer from catastrophic forgetting when acquiring new information.<n>We develop a neurally plausible continual learning model that achieves close to state-of-the-art accuracy (90%)<n>Our work provides a functional template for modeling memory consolidation, generalization, and continual learning in both biological and artificial systems.
  arXiv  Detail & Related papers  (2025-07-15T15:05:26Z)
• From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning [63.25540801694765]
  Large Language Models (LLMs) demonstrate striking linguistic abilities, yet whether they achieve this same balance remains unclear.<n>We apply the Information Bottleneck principle to quantitatively compare how LLMs and humans navigate this compression-meaning trade-off.
  arXiv  Detail & Related papers  (2025-05-21T16:29:00Z)
• Multi-task Collaborative Pre-training and Individual-adaptive-tokens Fine-tuning: A Unified Framework for Brain Representation Learning [3.1453938549636185]
  We propose a unified framework that combines Collaborative pre-training and Individual--Tokens fine-tuning. The proposed MCIAT achieves state-of-the-art diagnosis performance on the ADHD-200 dataset.
  arXiv  Detail & Related papers  (2023-06-20T08:38:17Z)
• NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants [73.85768093666582]
  We propose an explainable geometric deep network dubbed NeuroExplainer. NeuroExplainer is used to uncover altered infant cortical development patterns associated with preterm birth.
  arXiv  Detail & Related papers  (2023-01-01T12:48:12Z)
• Critical Learning Periods for Multisensory Integration in Deep Networks [112.40005682521638]
  We show that the ability of a neural network to integrate information from diverse sources hinges critically on being exposed to properly correlated signals during the early phases of training. We show that critical periods arise from the complex and unstable early transient dynamics, which are decisive of final performance of the trained system and their learned representations.
  arXiv  Detail & Related papers  (2022-10-06T23:50:38Z)
• Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks [107.8565143456161]
  We investigate the information processing strategies adopted by simple artificial neural networks performing a variety of cognitive tasks. Results show that synergy increases as neural networks learn multiple diverse tasks. randomly turning off neurons during training through dropout increases network redundancy, corresponding to an increase in robustness.
  arXiv  Detail & Related papers  (2022-10-06T15:36:27Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Object-based attention for spatio-temporal reasoning: Outperforming neuro-symbolic models with flexible distributed architectures [15.946511512356878]
  We show that a fully-learned neural network with the right inductive biases can perform substantially better than all previous neural-symbolic models. Our model makes critical use of both self-attention and learned "soft" object-centric representations.
  arXiv  Detail & Related papers  (2020-12-15T18:57:40Z)
• Brain-inspired self-organization with cellular neuromorphic computing for multimodal unsupervised learning [0.0]
  We propose a brain-inspired neural system based on the reentry theory using Self-Organizing Maps and Hebbian-like learning. We show the gain of the so-called hardware plasticity induced by the ReSOM, where the system's topology is not fixed by the user but learned along the system's experience through self-organization.
  arXiv  Detail & Related papers  (2020-04-11T21:02:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.