Reasoning Beyond Words ? Exploring framework for hidden state reasoning

2024/12/09 by Shibo Hao, Hao, Shibo, Sainbayar Sukhbaatar +11 · 40 voices · 308 citations
Computer Science · #Computer science #Geography #Linguistics #Meteorology #Natural Language Processing Techniques #Natural language processing #Philosophy #Space (punctuation) #Topic Modeling #Training (meteorology)

paper · pdf · doi:10.48550/arxiv.2412.06769

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2024/12/09 · openalex created_date 2024/12/12 · openalex updated_date 2026/07/28

Abstract

Large language models (LLMs) are typically constrained to reason in the language space, where they express the reasoning process through a chain-of-thought (CoT) to solve complex problems. However, the language space may not always be optimal for reasoning. Most word tokens primarily ensure textual coherence and are not essential for reasoning, while some critical tokens require complex planning and pose challenges to LLMs. To explore the potential of reasoning beyond language, we introduce a new paradigm called Coconut (Chain of Continuous Thought). Coconut utilizes the last hidden state of the LLM as a representation of the reasoning state, termed "continuous thought." Instead of decoding this state into words, we feed it back to the model as the next input embedding directly in the continuous space. This latent reasoning paradigm enables an advanced reasoning pattern, where continuous thoughts can encode multiple alternative next steps, allowing the model to perform a breadth-first search (BFS) rather than committing prematurely to a single deterministic path as in CoT. Coconut outperforms CoT on logical reasoning tasks that require substantial search during planning and achieves a better trade-off between accuracy and efficiency.

Cited by

• J-CoT: Chain-of-Thought in J-Space
• Pretraining Recurrent Networks without Recurrence
• SHIFT: Self-reconstruction Harnesses Implicit Fine-grained Thinking for Retrieval
• LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
• SLPO: Scaling Latent Reasoning via a Surrogate Policy
• Memoir: Should a Model Write to Its Memory While It Thinks?
• HiCI: Hierarchical Construction-Integration for Long-Context Attention
• LatentMT: Machine Translation with Latent Reasoning
• Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary
• MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering
• Constrained Path Reasoning: Measuring When Committed Stages Earn Their Cost
• T²MLR: Transformer with Temporal Middle-Layer Recurrence
• Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts
• MUX: Continuous Reasoning via Multiplexed Tokens
• Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
• Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
• Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
• Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
• Hierarchical Reasoning Model
• Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens
• Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
• Reasoning Models Can Be Effective Without Thinking
• Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
• Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
• Efficient Reasoning with Hidden Thinking
• Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models
• Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
• Machine Learning Decoding of Circuit-Level Noise for Bivariate Bicycle Codes
• DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
• The Case Against Generation for Retrieval: Discriminative Language Models as Effective Retrievers
• iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception
• Not All LLM Reasoning is Visible in the Chain-of-Thought
• Latent Implicit Visual Reasoning
• Observer, Not Player: Simulating Theory of Mind in LLMs through Game Observation
• JEPA-Reasoner: Decoupling Latent Reasoning from Token Generation
• Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs
• Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs
• DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
• From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition
• State over Tokens: Characterizing the Role of Reasoning Tokens
• Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
• VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
• Latent Chain-of-Thought World Modeling for End-to-End Driving
• Mull-Tokens: Modality-Agnostic Latent Thinking
• Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation
• Interleaved Latent Visual Reasoning with Selective Perceptual Modeling
• Generative Recursive Reasoning
• The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
• Unsupervised decoding of encoded reasoning using language model interpretability
• Lightweight Latent Reasoning for Narrative Tasks
• Difficulties with Evaluating a Deception Detector for AIs
• Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning
• Reinforcement Learning for Latent-Space Thinking in LLMs
• Latent Collaboration in Multi-Agent Systems
• CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
• Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
• Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement
• VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
• In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback
• SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving
• Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
• The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project
• SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
• C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning
• Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought
• Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
• Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding
• Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval
• EBT-Policy: Energy Unlocks Emergent Physical Reasoning Capabilities
• Penelope: Localized Latent Recurrence for Efficient Structured Reasoning
• Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning
• From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models
• Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
• HRM-Text: Efficient Pretraining Beyond Scaling
• Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought
• SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
• Improving LLM Reasoning via Dependency-Aware Query Decomposition and Logic-Parallel Content Expansion
• Parallel Loop Transformer for Efficient Test-Time Computation Scaling
• Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
• A Pragmatic Way to Measure Chain-of-Thought Monitorability
• HRM-Agent: Training a recurrent reasoning model in dynamic environments using reinforcement learning
• Context-level Language Modeling by Learning Predictive Context Embeddings
• A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring
• EffiReasonTrans: RL-Optimized Reasoning for Code Translation
• ActivationReasoning: Logical Reasoning in Latent Activation Spaces
• Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
• Soft-Masked Diffusion Language Models
• Planner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning
• LLM Latent Reasoning as Chain of Superposition
• Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism
• Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
• Towards Inference-time Scaling for Continuous Space Reasoning
• Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production
• Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States
• DND: Boosting Large Language Models with Dynamic Nested Depth
• Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning
• One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
• Concise Reasoning in the Lens of Lagrangian Optimization
• Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
• The Geometry of Reasoning: Flowing Logics in Representation Space
• Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges
• ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability
• Parallel Test-Time Scaling for Latent Reasoning Models
• R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
• MeSH: Memory-as-State-Highways for Recursive Transformers
• Can Speech LLMs Think while Listening?
• Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts
• CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
• Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
• Efficient numeracy in language models through single-token number embeddings
• KaVa: Latent Reasoning via Compressed KV-Cache Distillation
• Incoherence in Goal-Conditioned Autoregressive Models
• MixReasoning: Switching Modes to Think
• SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
• KEEP: Integrating Medical Ontologies with Clinical Data for Robust Code Embeddings
• LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
• Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
• The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
• What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
• Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner
• Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning
• Exploring System 1 and 2 communication for latent reasoning in LLMs
• Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
• Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space
• Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts
• Hierarchical Reasoning Models: Perspectives and Misconceptions
• LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
• MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
• Latent Visual Reasoning
• Learning to Ponder: Adaptive Reasoning in Latent Space
• Deep Thinking by Markov Chain of Continuous Thoughts
• Alternatives To Next Token Prediction In Text Generation -- A Survey
• Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
• Efficient Turing Machine Simulation with Transformers
• Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought
• Two-Scale Latent Dynamics for Recurrent-Depth Transformers
• PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space
• A model of errors in transformers
• MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning
• R-Capsule: Compressing High-Level Plans for Efficient Large Language Model Reasoning
• Learning to Reason with Mixture of Tokens
• A Formal Comparison Between Chain-of-Thought and Latent Thought
• SIM-CoT: Supervised Implicit Chain-of-Thought
• Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation
• Hierarchical Latent Reasoning for LLM-based Recommendation
• OPLD: On-Policy Latent Distillation for Multimodal Reasoning
• Can AI Follow In Einstein's Footsteps?
• SuperThoughts: Reasoning Tokens in Superposition
• LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation
• The Topological Trouble With Transformers
• Soft Tokens, Hard Truths
• OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System
• Stop Spinning Wheels: Mitigating LLM Overthinking via Mining Patterns for Early Reasoning Exit
• VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion
• Meta-R1: Empowering Large Reasoning Models with Metacognition
• Towards mitigating information leakage when evaluating safety monitors
• LTA-thinker: Latent Thought-Augmented Training Framework for Large Language Models on Complex Reasoning
• Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering
• Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization
• Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling
• From Long to Short: LLMs Excel at Trimming Own Reasoning Chains
• A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
• Implicit Reasoning in Large Language Models: A Comprehensive Survey
• Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
• Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics
• Reliable Weak-to-Strong Monitoring of LLM Agents
• Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis
• Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models
• Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models
• Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal
• Navigating Through Paper Flood: Advancing LLM-based Paper Evaluation through Domain-Aware Retrieval and Latent Reasoning
• LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking
• Compressing Chain-of-Thought in LLMs via Step Entropy
• Learning Temporal Abstractions via Variational Homomorphisms in Option-Induced Abstract MDPs
• SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought
• Enhancing Trustworthy Clinical Diagnosis Decision-Making in Large Language Models via Etiology-Aware Attention Supervision
• Explainability Through Systematicity: The Hard Systematicity Challenge for Artificial Intelligence
• Critique of impure reason: Unveiling the reasoning behaviour of medical large language models
• Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
• Unlocking the Working Memory of Large Language Models for Latent Reasoning
• Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation
• Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents
• GAVEL: Towards Rule-Based Safety Through Activation Monitoring
• Making Language Model a Hierarchical Classifier
• Change of Thought: Adaptive Test-Time Computation
• A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search
• ExpliCIT-QA: Explainable Code-Based Image Table Question Answering
• Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
• DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models
• AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition
• A Survey on Latent Reasoning
• Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning
• Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models
• ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoning
• Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer
• Energy-Based Transformers are Scalable Learners and Thinkers
• Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
• Demystifying Video Reasoning
• Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
• Improving Large Language Models with Concept-Aware Fine-Tuning
• Chain-of-Thought Enhanced Shallow Transformers for Wireless Symbol Detection
• ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation
• When Can Model-Free Reinforcement Learning be Enough for Thinking?
• Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
• On using AI for EEG-based BCI applications: problems, current challenges and future trends
• LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning
• Representation Consistency for Accurate and Coherent LLM Answer Aggregation
• Steering LLM Thinking with Budget Guidance
• Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models
• DART: Distilling Autoregressive Reasoning to Silent Thought
• What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding
• Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
• Scalable Chain of Thoughts via Elastic Reasoning
• Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
• Kinetics: Rethinking Test-Time Scaling Laws
• Crosslingual Reasoning through Test-Time Scaling
• LUT: Latent Utility Training for Visual Reasoning
• Agentic Graph Token Reasoning
• Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models
• OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
• Answer Convergence as a Signal for Early Stopping in Reasoning
• A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
• AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
• SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
• How do Transformers Learn Implicit Reasoning?
• Continuous Chain of Thought Enables Parallel Exploration and Reasoning
• Learning Composable Chains-of-Thought
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition
• Thinking with Generated Images
• Latent Reasoning via Sentence Embedding Prediction
• The Climb Carves Wisdom Deeper Than the Summit: On the Noisy Rewards in Learning to Reason
• Pretraining Language Models to Ponder in Continuous Space
• Can Past Experience Accelerate LLM Reasoning?
• Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition
• ARM: Adaptive Reasoning Model
• The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
• System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
• Reinforced Latent Reasoning for LLM-based Recommendation
• Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression
• Latent Thought Credit: Multi-Answer Credit Assignment for Latent Reasoning
• Anchored Diffusion Language Model
• Hybrid Latent Reasoning via Reinforcement Learning
• Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals
• VeriThinker: Learning to Verify Makes Reasoning Model Efficient
• Towards General Continuous Memory for Vision-Language Models
• Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
• TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
• Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
• Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
• R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search
• Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
• When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
• GRIT: Teaching MLLMs to Think with Images
• Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning
• FlashThink: An Early Exit Method For Efficient Reasoning
• Text Generation Beyond Discrete Token Sampling
• Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
• Scalable Autoregressive 3D Molecule Generation
• Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
• Recursive Vision Language Models for General Symbolic Reasoning
• Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
• Enhancing Latent Computation in Transformers with Latent Tokens
• Language Model Networks: Supervision-Efficient Learning through Dense Communication
• SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
• Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
• HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization
• SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning
• Sage Deer: A Super-Aligned Driving Generalist Is Your Copilot
• Accelerating Chain-of-Thought Reasoning: When Goal-Gradient Importance Meets Dynamic Skipping
• Entropy-Gated Latent Recursion
• CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
• HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models
• Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
• TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
• Latent Reasoning with Normalizing Flows
• ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation
• VLANeXt: Recipes for Building Strong VLA Models
• Training-Free Looped Transformers
• On the Failure of Latent State Persistence in Large Language Models
• Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
• Solve the Loop: Attractor Models for Language and Reasoning
• When Less is Enough: Efficient Inference via Collaborative Reasoning
• GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection
• Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
• Enhancing Non-Core Language Instruction-Following in Speech LLMs via Semi-Implicit Cross-Lingual CoT Reasoning
• How Transparent is DiffusionGemma?
• Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems
• Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
• Internalizing LLM Reasoning via Discovery and Replay of Latent Actions
• Efficient Reasoning for LLMs through Speculative Chain-of-Thought
• Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
• The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
• LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards
• Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
• Maglev: Sliding Recurrent Memory
• When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
• Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?
• Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering
• How to evaluate control measures for LLM agents? A trajectory from today to superintelligence
• Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
• Dynamic Early Exit in Reasoning Models
• FlowReasoner: Reinforcing Query-Level Meta-Agents
• Efficient Pretraining Length Scaling
• Efficient Reasoning Models: A Survey
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
• SEAL: Steerable Reasoning Calibration of Large Language Models for Free
• Feedback neural network [wikipedia]

Discussions

• Training LLMs to Reason in a Continuous Latent Space [hn, 283 points, 114 comments]
• Sometimes our anthropocentric assumptions about how intelligence "should" work (like using language for reasoning) may be holding AI back. Letting AI reason in its own native "language" in latent spac [bsky, 94 points, 5 comments]
• Training Large Language Models to Reason in a Continuous Latent Space Introduces a new paradigm for LLM reasoning called Chain of Continuous Thought (COCONUT) Directly feed the last hidden state (a [bsky, 54 points, 3 comments]
• uh oh. they're working on model architectures that reason and plan directly in latent space instead of using word-based chain of thought. Coconut and JEPA for example. we're neck-deep in unsettling co [bsky, 14 points, 2 comments]
• btw this was meant to try skipping tokenisation altogether, but it didn't seem to take off: arxiv.org/abs/2412.06769 [bsky, 10 points, 1 comments]
• Training Large Language Models to Reason in a Continuous Latent Space https://arxiv.org/abs/2412.06769v2 (attached screenshot from Andrew Ng’s newsletter) #AI #reasoning [bsky, 7 points, 0 comments]
• I always thought that reasoning does not require language. Well, this seems to be supported by neuroscience, see screenshot from arxiv.org/pdf/2412.06769 [bsky, 5 points, 0 comments]
• Pretty interesting paper by Meta & UC San Diego: arxiv.org/abs/2412.067... unlike humans, which don't activate the language network for many reasoning tasks, LLM are forced to reason in "language spac [bsky, 3 points, 1 comments]
• i have this paper in my queue. they basically just cut out the final layer that projects into logits and directly cycle the hidden layer output to the front of the LLM seems like what you’re looking [bsky, 3 points, 1 comments]
• A la arxiv.org/abs/2412.06769 [bsky, 2 points, 1 comments]
• Very cool paper on the internal dynamics of reasoning in LMs. The approach (Chain of Continuous Thought) lets models reason in continuous latent space rather than being constrained to generating speci [bsky, 2 points, 1 comments]
• Ce papier est fascinant et montre qu'une IA qu'on laisse définir des nouveaux concepts hors langage raisonne mieux. Ca fait sens : sur des problèmes complexes de math, je ne raisonne pas du tout en fr [bsky, 2 points, 0 comments]
• Your point about alien language reminded me of this paper: arxiv.org/abs/2412.06769 The LLMs are still trained in human languages but this 'continuous chain of thought approach' keeps the reasoning [bsky, 2 points, 0 comments]
• My attention was drawn recently to this paper. Some ML folks not only identified the fundamental design issue with LLMs which I've been going on about for a while, but it seems they also identified a [bsky, 1 points, 1 comments]
• There is some extra information you could preserve by saving the full-dimensional output at each position and using that as input instead of a token- that’s what arxiv.org/abs/2412.06769 is. It’s uncl [bsky, 1 points, 1 comments]
• I'm aware of these two recent papers implementing reasoning in latent space: - arxiv.org/abs/2412.06769 - arxiv.org/abs/2412.17747 [bsky, 1 points, 1 comments]
• Models can probably get better performance by reasoning in embedding space rather than in tokens (arxiv.org/pdf/2412.06769), I think we'll probably see large-scale models that reason entirely in laten [bsky, 1 points, 2 comments]
• Using the last state of the model as input without actually generating a token always seemed like an obvious idea. I guess it just took a long time to finish the paper. Great to see some results now. [bsky, 1 points, 0 comments]
• Here they utilize the last hidden state of the LLM as a representation of the reasoning state (termed "continuous thought"). Rather than decoding this into a word token, they feed it back to the LLM a [bsky, 1 points, 0 comments]
• The next paper I saw was on continuous chain of thought, creating new latent thoughts that are much more expressive and allow the model to compress its thinking by an OOM. arxiv.org/abs/2412.06769 [bsky, 1 points, 1 comments]
• Training Large Language Models to Reason in a Continuous Latent Space [pdf] [hn, 1 points, 0 comments]
• Training LLMs to Reason in a Continuous Latent Space https://arxiv.org/abs/2412.06769 (https://news.ycombinator.com/item?id=42378335) [bsky, 0 points, 0 comments]
• I think I only understand like 50% of this but it's v cool arxiv.org/abs/2412.06769 - the general idea of feeding latent cognition back into the inference instead of having every input being a previou [bsky, 0 points, 1 comments]
• Training LLMs to Reason in a Continuous Latent Space [bsky, 0 points, 0 comments]
• Meta and UC San Diego's Coconut framework enhances LLM reasoning by utilizing continuous latent space for improved planning and efficiency, allows reasoning without being limited by words. arxiv.org/a [bsky, 0 points, 0 comments]
• Interesting paper from Meta shows how letting AI models reason directly in neural space, rather than through tokens, leads to more efficient and flexible problem-solving arxiv.org/pdf/2412.06769 [bsky, 0 points, 0 comments]
• I don't think that's the current prevalent narrative in many circles. So much focus now is on reasoning models which is quite a different thing from a single pass through an LLM. And the new paper on [bsky, 0 points, 1 comments]
• Paper from Meta that describes “continuous thinking in latent space” in a way that can’t be done with GPT and chain of thought (CoT) reasoning. arxiv.org/pdf/2412.06769 *Worse* than Chain-of-thought [bsky, 0 points, 0 comments]
• Training LLMs to Reason in a Continuous Latent Space Research exploring advanced reasoning capabilities for large language models, potentially improving AI reasoning and problem-solving Read here [bsky, 0 points, 0 comments]
• Training LLMs to Reason in a Continuous Latent Space (arxiv.org) Main Link | Discussion [bsky, 0 points, 0 comments]
• Training Large Language Models to Reason in a Continuous Latent Space "We utilize the last hidden state of the LLM as a representation of the reasoning state...we feed it back to the LLM as the subseq [bsky, 0 points, 0 comments]
• Would love to see more work on reasoning in the concept space for LLM, like in this paper: arxiv.org/abs/2412.06769 [bsky, 0 points, 0 comments]
• Training LLMs to Reason in a Continuous Latent Space https://arxiv.org/abs/2412.06769 (https://news.ycombinator.com/item?id=42378335) [bsky, 0 points, 0 comments]
• How about 'Breadth-First Latent Reasoning'? Additionally, this represents a significant improvement in LLM reasoning. arxiv.org/abs/2412.06769 [bsky, 0 points, 1 comments]
• No More Words: Does reasoning require language? A new paper suggests that for certain kinds of problems AI reasoning models are better off leaving words behind. arxiv.org/abs/2412.06769 [bsky, 0 points, 1 comments]
• Training LLMs to Reason in a Continuous Latent Space https://arxiv.org/abs/2412.06769 [comments] [116 points] [bsky, 0 points, 0 comments]
• Training LLMs to Reason in a Continuous Latent Space https://arxiv.org/abs/2412.06769 arxiv.org [bsky, 0 points, 0 comments]
• Here is a “demo” that, given a tradeoff between AI transparency (English-language chain-of-thought) and AI capability (inscrutable chain-of-thought but the results are better), many people will choose [bsky, 0 points, 1 comments]
• What really grabbed me is how COCONUT mimics a "thought process" through these continuous latent trajectories. It’s like the AI is creating its own mental map to solve complex tasks! The planning par [bsky, 0 points, 2 comments]
• Training LLMs to Reason in a Continuous Latent Space https://arxiv.org/abs/2412.06769 https://news.ycombinator.com/item?id=42378335 [bsky, 0 points, 0 comments]

Related

• SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs
• Deep Thinking by Markov Chain of Continuous Thoughts
• Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
• Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models
• Chain-of-Thought Reasoning Without Prompting