CORE: A Conceptual Reasoning Layer for Large Language Models

• URL: http://arxiv.org/abs/2512.09222v1
• Date: Wed, 10 Dec 2025 01:08:06 GMT
• Title: CORE: A Conceptual Reasoning Layer for Large Language Models
• Authors: Vishwas Hegde, Vindhya Shigehalli,
• Abstract summary: CORE is a concept-first interaction layer that improves multi-turn stability without modifying model weights.<n> CORE combines a small library of universal cognitive operators with a persistent Local Concept.<n>Preliminary prototype simulating CORE's behavior shows about 42% reduction in cumulative prompt tokens.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across turns. This token-first paradigm leads to drift, inconsistent reasoning modes, and growing prompts as conversations deepen. We propose CORE, a concept-first interaction layer that improves multi-turn stability without modifying model weights. CORE combines a small library of universal cognitive operators with a persistent Local Concept - a compact semantic state capturing the task, constraints, preferences, and intermediate results. Each model call receives only this concept state, the user's latest instruction, and the selected operator, eliminating the need to replay full history. A preliminary prototype simulating CORE's behavior shows about 42% reduction in cumulative prompt tokens, though this number reflects prototype conditions and should not be interpreted as a real-world performance estimate. CORE offers a model-agnostic mechanism that separates conceptual reasoning from language generation, suggesting a scalable direction for more stable multi-turn systems.

Related papers

• Kelix Technical Report [86.64551727600104]
  We present Kelix, a fully discrete autoregressive unified model that closes the understanding gap between discrete and continuous visual representations.<n>Recent work has explored discrete visual tokenization to enable fully autoregressive multimodal modeling.
  arXiv  Detail & Related papers  (2026-02-10T14:48:26Z)
• Structured Cognitive Loop for Behavioral Intelligence in Large Language Model Agents [0.0]
  Existing frameworks often mix cognition, memory, and control in a single prompt, reducing coherence and predictability.<n>The Structured Cognitive Loop (SCL) is proposed as an alternative architecture that separates these functions.<n>SCL achieves an average task success rate of 86.3 percent, compared with 70.5 to 76.8 percent for baselines.
  arXiv  Detail & Related papers  (2025-09-23T17:43:17Z)
• PyLate: Flexible Training and Retrieval for Late Interaction Models [3.737581531719168]
  We introduce PyLate, a library built on top of Sentence Transformers to support multi-vector architectures.<n>By offering multi-vector-specific features such as efficient indexes, PyLate aims to accelerate research and real-world application of late interaction models.<n> PyLate has already enabled the development of state-of-the-art models, including GTE-ModernColBERT and Reason-ModernColBERT.
  arXiv  Detail & Related papers  (2025-08-05T15:23:40Z)
• Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models [54.85405423240165]
  We introduce Interactive Reasoning, an interaction design that visualizes chain-of-thought outputs as a hierarchy of topics.<n>We implement interactive reasoning in Hippo, a prototype for AI-assisted decision making in the face of uncertain trade-offs.
  arXiv  Detail & Related papers  (2025-06-30T10:00:43Z)
• Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation [49.45822979879046]
  Generative recommendation (GR) typically encodes behavioral or semantic aspects of item information into discrete tokens.<n>We present Chunk AutoRegressive Modeling (CAR), a new generation paradigm following the decision pattern that users usually think semantic aspects of items.
  arXiv  Detail & Related papers  (2025-06-30T09:13:54Z)
• Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection [37.57355457749918]
  We introduce a novel framework for zero-shot HOI detection using Conditional Multi-Modal Prompts, namely CMMP. Unlike traditional prompt-learning methods, we propose learning decoupled vision and language prompts for interactiveness-aware visual feature extraction. Experiments demonstrate the efficacy of our detector with conditional multi-modal prompts, outperforming previous state-of-the-art on unseen classes of various zero-shot settings.
  arXiv  Detail & Related papers  (2024-08-05T14:05:25Z)
• Auxiliary Losses for Learning Generalizable Concept-based Models [5.4066453042367435]
  Concept Bottleneck Models (CBMs) have gained popularity since their introduction. CBMs essentially limit the latent space of a model to human-understandable high-level concepts. We propose cooperative-Concept Bottleneck Model (coop-CBM) to overcome the performance trade-off.
  arXiv  Detail & Related papers  (2023-11-18T15:50:07Z)
• Collaborative Development of NLP models [6.22933818252838]
  We introduce CoDev, a framework that enables multi-user interaction with NLP models. CoDev aids users in operationalizing their concepts using Large Language Models. We then steer a large language model to generate instances within concept boundaries where local and global disagree.
  arXiv  Detail & Related papers  (2023-05-20T15:55:39Z)
• Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings [61.04460792203266]
  We introduce VCoT, a novel method that leverages chain-of-thought prompting with vision-language grounding to bridge the logical gaps within sequential data. Our method uses visual guidance to generate synthetic multimodal infillings that add consistent and novel information to reduce the logical gaps for downstream tasks.
  arXiv  Detail & Related papers  (2023-05-03T17:58:29Z)
• Bayesian Prompt Learning for Image-Language Model Generalization [64.50204877434878]
  We use the regularization ability of Bayesian methods to frame prompt learning as a variational inference problem. Our approach regularizes the prompt space, reduces overfitting to the seen prompts and improves the prompt generalization on unseen prompts. We demonstrate empirically on 15 benchmarks that Bayesian prompt learning provides an appropriate coverage of the prompt space.
  arXiv  Detail & Related papers  (2022-10-05T17:05:56Z)
• Twist Decoding: Diverse Generators Guide Each Other [116.20780037268801]
  We introduce Twist decoding, a simple and general inference algorithm that generates text while benefiting from diverse models. Our method does not assume the vocabulary, tokenization or even generation order is shared.
  arXiv  Detail & Related papers  (2022-05-19T01:27:53Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)

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.