{"total":28,"rows":[{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2505.22411","title":"Mitigating Overthinking in Large Reasoning Models via Manifold Steering","created":"2025-05-28","cited_by_count":33,"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":"2507.22928","title":"How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding","created":"2025-07-24","cited_by_count":19,"area":"lr"},{"id":"2501.06254","title":"Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words","created":"2025-01-09","cited_by_count":18,"area":"lr"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2502.09192","title":"Thinking beyond the anthropomorphic paradigm benefits LLM research","created":"2025-02-13","cited_by_count":14,"area":"lr"},{"id":"2506.01115","title":"Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2502.09022","title":"Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning","created":"2025-02-13","cited_by_count":11,"area":"lr"},{"id":"2509.25758","title":"Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2506.21590","title":"Representation Consistency for Accurate and Coherent LLM Answer Aggregation","created":"2025-06-18","cited_by_count":5,"area":"lr"},{"id":"2512.12777","title":"State over Tokens: Characterizing the Role of Reasoning Tokens","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2509.06332","title":"A Fragile Number Sense: Probing the Elemental Limits of Numerical Reasoning in LLMs","created":"2025-09-08","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":"2504.00226","title":"Large Language Models in Numberland: A Quick Test of Their Numerical Reasoning Abilities","created":"2025-03-31","cited_by_count":2,"area":"lr"},{"id":"2506.00577","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","created":"2025-05-31","cited_by_count":2,"area":"lr"},{"id":"2511.20344","title":"The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models","created":"2025-11-25","cited_by_count":2,"area":"lr"},{"id":"2602.08693","title":"Reasoning aligns language models to human cognition","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2507.22940","title":"Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes","created":"2025-07-25","cited_by_count":1,"area":"lr"},{"id":"2511.04053","title":"Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models","created":"2025-11-06","cited_by_count":0,"area":"lr"},{"id":"2603.10225","title":"Rethinking the Harmonic Loss via Non-Euclidean Distance Layers","created":"2026-03-10","cited_by_count":0,"area":"lr"},{"id":"2604.20039","title":"Separable Pathways for Causal Reasoning: How Architectural Scaffolding Enables Hypothesis-Space Restructuring in LLM Agents","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2605.22902","title":"Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.06840","title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2607.13899","title":"AIMO Interpretability Challenge","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2609.03511","title":"Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations","created":"2026-09-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}