{"total":117,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2511.20639","title":"Latent Collaboration in Multi-Agent Systems","created":"2025-11-25","cited_by_count":73,"area":"lr"},{"id":"2509.20317","title":"SIM-CoT: Supervised Implicit Chain-of-Thought","created":"2025-09-24","cited_by_count":70,"area":"lr"},{"id":"2509.02350","title":"Implicit Reasoning in Large Language Models: A Comprehensive Survey","created":"2025-09-02","cited_by_count":43,"area":"lr"},{"id":"2604.02029","title":"The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook","created":"2026-04-02","cited_by_count":43,"area":null},{"id":"2510.15522","title":"LLM Latent Reasoning as Chain of Superposition","created":"2025-10-17","cited_by_count":39,"area":"lr"},{"id":"2508.03440","title":"LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking","created":"2025-08-05","cited_by_count":38,"area":"lr"},{"id":"2505.23648","title":"Continuous Chain of Thought Enables Parallel Exploration and Reasoning","created":"2025-05-29","cited_by_count":35,"area":"lr"},{"id":"2509.19170","title":"Soft Tokens, Hard Truths","created":"2025-09-23","cited_by_count":35,"area":"lr"},{"id":"2510.04573","title":"LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning","created":"2025-10-06","cited_by_count":29,"area":"lr"},{"id":"2512.12623","title":"Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space","created":"2025-12-14","cited_by_count":28,"area":"lr"},{"id":"2512.16584","title":"Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs","created":"2025-12-18","cited_by_count":25,"area":"lr"},{"id":"2601.09708","title":"Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning","created":"2026-01-14","cited_by_count":24,"area":"vla"},{"id":"2510.05069","title":"SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs","created":"2025-10-06","cited_by_count":22,"area":"lr"},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"area":"lr"},{"id":"2511.06411","title":"SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization","created":"2025-11-09","cited_by_count":21,"area":"lr"},{"id":"2605.19376","title":"Generative Recursive Reasoning","created":"2026-05-19","cited_by_count":20,"area":null},{"id":"2510.17206","title":"Soft-Masked Diffusion Language Models","created":"2025-10-20","cited_by_count":16,"area":"diffusion"},{"id":"2511.08577","title":"Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning","created":"2025-11-11","cited_by_count":16,"area":"lr"},{"id":"2601.08808","title":"Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge","created":"2026-01-13","cited_by_count":16,"area":"lr"},{"id":"2507.08182","title":"CTRLS: Chain-of-Thought Reasoning via Latent State-Transition","created":"2025-07-10","cited_by_count":14,"area":"lr"},{"id":"2510.07745","title":"Parallel Test-Time Scaling for Latent Reasoning Models","created":"2025-10-09","cited_by_count":14,"area":"lr"},{"id":"2603.13366","title":"Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding","created":"2026-03-09","cited_by_count":12,"area":"lr"},{"id":"2510.19669","title":"DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference","created":"2025-10-22","cited_by_count":11,"area":"lr"},{"id":"2602.08783","title":"Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2512.24574","title":"Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time","created":"2025-12-31","cited_by_count":10,"area":"lr"},{"id":"2601.22954","title":"Residual Context Diffusion Language Models","created":"2026-01-30","cited_by_count":10,"area":"diffusion"},{"id":"2603.01914","title":"AdaPonderLM: Gated Pondering Language Models with Token-Wise Adaptive Depth","created":"2026-03-02","cited_by_count":10,"area":"lr"},{"id":"2604.27998","title":"Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning","created":"2026-04-30","cited_by_count":10,"area":"lr"},{"id":"2509.24248","title":"SpecExit: Accelerating Large Reasoning Model via Speculative Exit","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2510.11052","title":"Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2602.15382","title":"The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems","created":"2026-02-17","cited_by_count":9,"area":"lr"},{"id":"2505.23701","title":"Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2511.02360","title":"LaRe: Latent Refocusing for Multimodal Reasoning","created":"2025-11-04","cited_by_count":8,"area":"lr"},{"id":"2602.11683","title":"ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2603.09786","title":"Quantifying the Necessity of Chain of Thought through Opaque Serial Depth","created":"2026-03-10","cited_by_count":8,"area":"lr"},{"id":"2604.22709","title":"Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought","created":"2026-04-24","cited_by_count":8,"area":"lr"},{"id":"2605.11856","title":"UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs","created":"2026-05-12","cited_by_count":8,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2604.06374","title":"The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models","created":"2026-04-07","cited_by_count":7,"area":"lr"},{"id":"2604.08299","title":"SeLaR: Selective Latent Reasoning in Large Language Models","created":"2026-04-09","cited_by_count":7,"area":"lr"},{"id":"2607.15178","title":"T^2MLR: Transformer with Temporal Middle-Layer Recurrence","created":"2026-07-16","cited_by_count":7,"area":null},{"id":"2510.00494","title":"Exploring System 1 and 2 communication for latent reasoning in LLMs","created":"2025-10-01","cited_by_count":6,"area":"lr"},{"id":"2601.07351","title":"Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models","created":"2026-01-12","cited_by_count":6,"area":"diffusion"},{"id":"2601.21358","title":"Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization","created":"2026-01-29","cited_by_count":6,"area":"lr"},{"id":"2602.09850","title":"Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning","created":"2026-02-10","cited_by_count":6,"area":"lr"},{"id":"2603.12252","title":"EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models","created":"2026-03-12","cited_by_count":6,"area":"lr"},{"id":"2603.12529","title":"TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning","created":"2026-03-13","cited_by_count":6,"area":"lr"},{"id":"2603.17837","title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2604.20328","title":"HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization","created":"2026-04-22","cited_by_count":6,"area":"lr"},{"id":"2506.23864","title":"Garbage In, Reasoning Out? Why Benchmark Scores are Unreliable and What to Do About It","created":"2025-06-30","cited_by_count":5,"area":"lr"},{"id":"2512.23988","title":"Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process","created":"2025-12-30","cited_by_count":5,"area":"lr"},{"id":"2608.08888","title":"Full-bandwidth transformer","created":"2026-08-09","cited_by_count":5,"area":null},{"id":"2602.01148","title":"Capabilities and Fundamental Limits of Latent Chain-of-Thought","created":"2026-02-01","cited_by_count":4,"area":"lr"},{"id":"2602.01698","title":"Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2602.10229","title":"Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","cited_by_count":4,"area":"lr"},{"id":"2604.03679","title":"LightThinker++: From Reasoning Compression to Memory Management","created":"2026-04-04","cited_by_count":4,"area":"lr"},{"id":"2604.17892","title":"LEPO: Latent Reasoning Policy Optimization for Large Language Models","created":"2026-04-20","cited_by_count":4,"area":"lr"},{"id":"2606.06447","title":"Latent Reasoning with Normalizing Flows","created":"2026-06-04","cited_by_count":4,"area":"lr"},{"id":"2606.12689","title":"Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models","created":"2026-06-10","cited_by_count":4,"area":"lr"},{"id":"2607.00341","title":"DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning","created":"2026-07-01","cited_by_count":4,"area":"lr"},{"id":"2509.21482","title":"Learning to Reason with Mixture of Tokens","created":"2025-09-25","cited_by_count":3,"area":"lr"},{"id":"2511.08983","title":"SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving","created":"2025-11-12","cited_by_count":3,"area":"lr"},{"id":"2603.01331","title":"MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2605.09969","title":"The Truth Lies Somewhere in the Middle (of the Generated Tokens)","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2606.01243","title":"Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention","created":"2026-05-31","cited_by_count":3,"area":"lr"},{"id":"2506.07833","title":"Improving Large Language Models with Concept-Aware Fine-Tuning","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2509.01619","title":"Throttling Web Agents Using Reasoning Gates","created":"2025-09-01","cited_by_count":2,"area":"lr"},{"id":"2511.16885","title":"Improving Latent Reasoning in LLMs via Soft Concept Mixing","created":"2025-11-21","cited_by_count":2,"area":"lr"},{"id":"2602.14917","title":"BFS-PO: Best-First Search for Large Reasoning Models","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2605.27255","title":"Pair-In, Pair-Out: Latent Multi-Token Prediction for Efficient LLMs","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2606.13106","title":"Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning","created":"2026-06-11","cited_by_count":2,"area":"lr"},{"id":"2606.13945","title":"LatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2606.15160","title":"DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning","created":"2026-06-13","cited_by_count":2,"area":"wm"},{"id":"2606.25354","title":"Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing","created":"2026-06-24","cited_by_count":2,"area":"lr"},{"id":"2607.16972","title":"Training Continuous Chain of Thought Models: A Tale of Two Regimes","created":"2026-07-18","cited_by_count":2,"area":"lr"},{"id":"2510.03727","title":"Bridging the Gap Between Multimodal Foundation Models and World Models","created":"2025-10-04","cited_by_count":1,"area":"wm"},{"id":"2511.10201","title":"EffiReason-Bench: A Unified Benchmark for Evaluating and Advancing Efficient Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2603.29123","title":"Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2605.16961","title":"Latent Action Control for Reasoning-Guided Unified Image Generation","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2605.20075","title":"CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2605.24140","title":"HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2608.24136","title":"Steering Recurrent Reasoners at Inference Time with Readout Feedback","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.09928","title":"Structural Process Supervision for Latent Chain-of-Thought Reasoning","created":"2026-09-09","cited_by_count":1,"area":"lr"},{"id":"2512.01485","title":"Multi-Path Collaborative Reasoning via Reinforcement Learning","created":"2025-12-01","cited_by_count":0,"area":"lr"},{"id":"2606.01168","title":"Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2606.02248","title":"Geometric Latent Reasoning Induces Shorter Generations in LLMs","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2606.07108","title":"DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.10184","title":"Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning","created":"2026-06-08","cited_by_count":0,"area":"lr"},{"id":"2606.10572","title":"One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA","created":"2026-06-09","cited_by_count":0,"area":"mllm"},{"id":"2606.10768","title":"N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.13862","title":"SuperThoughts: Reasoning Tokens in Superposition","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.29928","title":"Latent-CURE for Breast Cancer Diagnosis","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.19691","title":"SLPO: Scaling Latent Reasoning via a Surrogate Policy","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2607.19932","title":"Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2608.03450","title":"Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.09888","title":"BDH-CQ: In-Context Learning with Recurrent Latent Reasoning","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2608.31069","title":"A Model with No Head and Many Thoughts","created":"2026-08-31","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}