Think Deep, Speak Once: Relit, A Recursive Latent Implicit Transformer Framework
Abhishek Panwar, Maheep Singh, Saksham Bansal
cs.AI
Submitted: 2026-08-08
Updated: 2026-08-11
Comments: 14 pages, 6 figures
Code: https://github.com/mdgspace/Think-Deep-Speak-Once-ReLIT
License: http://creativecommons.org/licenses/by/4.0/
The gist: Chain-of-Thought (CoT) prompting has become the dominant paradigm for eliciting reasoning in Large Language Models (LLMs), yet it creates substantial computational overhead by forcing models to
Terminology
Abstract
Chain-of-Thought (CoT) prompting has become the dominant paradigm for eliciting reasoning in Large Language Models (LLMs), yet it creates substantial computational overhead by forcing models to externalize intermediate reasoning steps as discrete tokens. Recent latent reasoning approaches attempt to internalize this process within continuous hidden states. One of the latest advancements in the field of latent reasoning, Tiny Recursive Models (TRMs) excel at symbolic reasoning but struggle to preserve semantic coherence in natural language settings. To bridge this gap, we introduce ReLIT (Recursive Latent Implicit Transformer), a hybrid framework that grounds deep recursive reasoning within the rich semantic representations of a foundational model. ReLIT augments a frozen LLM backbone (TinyLlama-1.1B) with a lightweight, trainable recursive block that iteratively refines its latent thinking (z) before committing to a final output, structurally solving linguistic intuition from algorithmic processing and enabling "deep thinking" via gradient-isolated recurrent loops without the latency of explicit token generation. Empirically, ReLIT achieves high parameter efficiency on the GLoRE logical reasoning benchmark, matching or outperforming significantly larger models on challenging tasks such as ProofWriter and RuleTaker despite minimal supervision. These results demonstrate that reasoning capability can be scaled efficiently through recurrent depth rather than parameter width, offering a principled framework for semantically grounded implicit reasoning.
Sources
- Backpropagation Through Time For Networks With Long-Term Dependencies
- Universal Transformers
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- Adaptive Computation Time for Recurrent Neural Networks
- Training Large Language Models to Reason in a Continuous Latent Space
- Deeply-Supervised Nets
- "Understanding AI": Semantic Grounding in Large Language Models
- GLU Variants Improve Transformer
- Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
- Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation
- Hierarchical Reasoning Model
- Root Mean Square Layer Normalization
- TinyLlama: An Open-Source Small Language Model
- A Survey on Latent Reasoning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems