{"total":72,"rows":[{"id":"2506.19143","title":"Thought Anchors: Which LLM Reasoning Steps Matter?","created":"2025-06-23","cited_by_count":129,"area":"lr"},{"id":"2603.05488","title":"Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought","created":"2026-03-05","cited_by_count":40,"area":"lr"},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2510.07364","title":"Base Models Know How to Reason, Thinking Models Learn When","created":"2025-10-08","cited_by_count":27,"area":"lr"},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2507.12638","title":"Reasoning-Finetuning Repurposes Latent Representations in Base Models","created":"2025-07-16","cited_by_count":26,"area":"lr"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2510.01290","title":"ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models","created":"2025-10-01","cited_by_count":21,"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":"2510.24941","title":"Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought","created":"2025-10-28","cited_by_count":15,"area":"lr"},{"id":"2511.06419","title":"MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models","created":"2025-11-09","cited_by_count":12,"area":"lr"},{"id":"2601.05679","title":"Do Sparse Autoencoders Identify Reasoning Features in Language Models?","created":"2026-01-09","cited_by_count":12,"area":"lr"},{"id":"2601.10825","title":"Reasoning Models Generate Societies of Thought","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2511.07772","title":"SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought","created":"2025-11-11","cited_by_count":11,"area":"lr"},{"id":"2509.23799","title":"Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement","created":"2025-09-28","cited_by_count":10,"area":"mechinterp"},{"id":"2510.04217","title":"MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering","created":"2025-10-05","cited_by_count":10,"area":"mllm"},{"id":"2603.22161","title":"Causal Evidence that Language Models use Confidence to Drive Behavior","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2509.06608","title":"Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors","created":"2025-09-08","cited_by_count":8,"area":"lr"},{"id":"2512.19995","title":"Schoenfeld's Anatomy of Mathematical Reasoning by Language Models","created":"2025-12-23","cited_by_count":8,"area":"lr"},{"id":"2604.09839","title":"Steered LLM Activations are Non-Surjective","created":"2026-04-10","cited_by_count":8,"area":"mechinterp"},{"id":"2604.08524","title":"What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal","created":"2026-04-09","cited_by_count":7,"area":"alignment"},{"id":"2606.17056","title":"The Value Axis: Language Models Encode Whether They're on the Right Track","created":"2026-06-15","cited_by_count":7,"area":null},{"id":"2509.23782","title":"Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2510.04128","title":"Internal states before wait modulate reasoning patterns","created":"2025-10-05","cited_by_count":6,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2507.02332","title":"PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage","created":"2025-07-03","cited_by_count":5,"area":"alignment"},{"id":"2509.16820","title":"DISCO: Disentangled Communication Steering for Large Language Models","created":"2025-09-20","cited_by_count":5,"area":"mechinterp"},{"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":"2605.29192","title":"ReasonOps: Operator Segmentation for LLM Reasoning Traces","created":"2026-05-28","cited_by_count":5,"area":"lr"},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5,"area":"lr"},{"id":"2511.06739","title":"Rank-1 LoRAs Encode Interpretable Reasoning Signals","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2510.12063","title":"ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization","created":"2025-10-14","cited_by_count":3,"area":"lr"},{"id":"2510.22437","title":"Modeling Hierarchical Thinking in Large Reasoning Models","created":"2025-10-25","cited_by_count":3,"area":"lr"},{"id":"2604.01161","title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2510.19476","title":"A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2510.19875","title":"Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention","created":"2025-10-22","cited_by_count":2,"area":"mechinterp"},{"id":"2602.05810","title":"Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents","created":"2026-02-05","cited_by_count":2,"area":"synth"},{"id":"2603.01822","title":"Emerging Human-like Strategies for Semantic Memory Foraging in Large Language Models","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.14636","title":"Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models","created":"2026-03-15","cited_by_count":2,"area":"lr"},{"id":"2606.06188","title":"The Tell-Tale Norm: $\\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2510.18154","title":"Annotating the Chain-of-Thought: A Behavior-Labeled Dataset for AI Safety","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2510.22389","title":"Can Small and Reasoning Large Language Models Score Journal Articles for Research Quality and Do Averaging and Few-shot Help?","created":"2025-10-25","cited_by_count":1,"area":"lr"},{"id":"2602.06266","title":"Is my model \"mind blurting\"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)","created":"2026-02-05","cited_by_count":1,"area":"lr"},{"id":"2603.19118","title":"How Uncertainty Estimation Scales with Sampling in Reasoning Models","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2603.22754","title":"PRISM: A Dual View of LLM Reasoning through Semantic Flow and Latent Computation","created":"2026-03-24","cited_by_count":1,"area":"lr"},{"id":"2604.02113","title":"Reliable Control-Point Selection for Steering Reasoning in Large Language Models","created":"2026-04-02","cited_by_count":1,"area":"lr"},{"id":"2604.06377","title":"The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2604.19001","title":"HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2604.19149","title":"How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2606.03965","title":"Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.15092","title":"High-Dimensional Random Projection for Activation Steering in Language Models","created":"2026-06-13","cited_by_count":1,"area":"mechinterp"},{"id":"2608.03291","title":"The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2609.38342","title":"Activation-Conditioned Self-Distillation","created":"2026-09-29","cited_by_count":1,"area":"distill"},{"id":"2602.02160","title":"D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.04843","title":"Fluid Reasoning Representations","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2604.23877","title":"Knowledge Vector of Logical Reasoning in Large Language Models","created":"2026-04-26","cited_by_count":0,"area":"lr"},{"id":"2605.08188","title":"Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.08254","title":"HyperTransport: Amortized Conditioning of T2I Generative Models","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2605.17278","title":"A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation","created":"2026-05-17","cited_by_count":0,"area":"lr"},{"id":"2606.17735","title":"Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2607.05185","title":"ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.24471","title":"Grounding latent algorithm routing in transformer reasoning","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2608.27348","title":"INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.06879","title":"AutoLexSteer: Automatic Contrast Construction for Lexical Activation Steering","created":"2026-09-06","cited_by_count":0,"area":"mechinterp"},{"id":"2609.10123","title":"If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.16245","title":"Metacognitive Steering: Learning the Structure of Scientific Judgment","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.28682","title":"Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.35599","title":"Signatures of semantic search in the activations of large language models","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2610.01062","title":"Kernelized Activation Steering","created":"2026-10-01","cited_by_count":0,"area":"mechinterp"},{"id":"2610.07572","title":"Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings","created":"2026-10-06","cited_by_count":0,"area":"mllm"},{"id":"2610.14270","title":"The Thinking Leakage in Reinforcement Learning for LLMs","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}