{"total":113,"rows":[{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2510.17638","title":"LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena","created":"2025-10-20","cited_by_count":40,"area":null},{"id":"2504.05047","title":"Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning","created":"2025-04-07","cited_by_count":27,"area":"lr"},{"id":"2510.03222","title":"Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward","created":"2025-10-03","cited_by_count":25,"area":"lr"},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"area":null},{"id":"2510.10409","title":"Trace Length is a Simple Uncertainty Signal in Reasoning Models","created":"2025-10-12","cited_by_count":19,"area":"lr"},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18,"area":null},{"id":"2509.24282","title":"SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents","created":"2025-09-29","cited_by_count":15,"area":"agents"},{"id":"2509.24086","title":"Do Repetitions Matter? Strengthening Reliability in LLM Evaluations","created":"2025-09-28","cited_by_count":14,"area":null},{"id":"2509.25532","title":"Calibrating Verbalized Confidence with Self-Generated Distractors","created":"2025-09-29","cited_by_count":14,"area":"synth"},{"id":"2602.03845","title":"Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing","created":"2026-02-03","cited_by_count":14,"area":null},{"id":"2509.13813","title":"Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs","created":"2025-09-17","cited_by_count":13,"area":null},{"id":"2509.13990","title":"Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency","created":"2025-09-17","cited_by_count":13,"area":"lr"},{"id":"2601.02970","title":"Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning","created":"2026-01-06","cited_by_count":11,"area":"lr"},{"id":"2504.10368","title":"Exploring the System 1 Thinking Capability of Large Reasoning Models","created":"2025-04-14","cited_by_count":10,"area":"lr"},{"id":"2508.21787","title":"PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains","created":"2025-08-29","cited_by_count":10,"area":"lr"},{"id":"2510.13855","title":"Harnessing Consistency for Robust Test-Time LLM Ensemble","created":"2025-10-12","cited_by_count":10,"area":null},{"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":"2603.20215","title":"Multi-Agent Debate with Memory Masking","created":"2026-03-03","cited_by_count":10,"area":"lr"},{"id":"2605.08083","title":"LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling","created":"2026-05-08","cited_by_count":10,"area":"lr"},{"id":"2511.12309","title":"Optimal Self-Consistency for Efficient Reasoning with Large Language Models","created":"2025-11-15","cited_by_count":9,"area":"lr"},{"id":"2505.17454","title":"Self-Training Large Language Models with Confident Reasoning","created":"2025-05-23","cited_by_count":8,"area":"lr"},{"id":"2505.20325","title":"Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence","created":"2025-05-23","cited_by_count":8,"area":"lr"},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2603.06616","title":"RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models","created":"2026-02-20","cited_by_count":7,"area":null},{"id":"2604.03216","title":"BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence","created":"2026-04-03","cited_by_count":7,"area":null},{"id":"2508.20395","title":"Measuring Reasoning Utility in LLMs via Conditional Entropy Reduction","created":"2025-08-28","cited_by_count":6,"area":"lr"},{"id":"2510.02377","title":"Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems","created":"2025-09-30","cited_by_count":6,"area":"lr"},{"id":"2602.18232","title":"Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning","created":"2026-02-20","cited_by_count":6,"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":"2508.12393","title":"MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph","created":"2025-08-17","cited_by_count":5,"area":"agents"},{"id":"2510.06261","title":"AlphaApollo: A System for Deep Agentic Reasoning","created":"2025-10-05","cited_by_count":5,"area":"agents"},{"id":"2602.12916","title":"Reliable Thinking with Images","created":"2026-02-13","cited_by_count":5,"area":"lr"},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","cited_by_count":5,"area":null},{"id":"2509.17238","title":"MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE","created":"2025-09-21","cited_by_count":4,"area":"lr"},{"id":"2510.05126","title":"Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2511.02130","title":"Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning","created":"2025-11-03","cited_by_count":4,"area":"lr"},{"id":"2604.06794","title":"GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering","created":"2026-04-08","cited_by_count":4,"area":"lr"},{"id":"2604.17274","title":"Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models","created":"2026-04-19","cited_by_count":4,"area":"mllm"},{"id":"2605.29116","title":"Beyond Consensus: Trace-Level Synthesis in Mixture of Agents","created":"2026-05-27","cited_by_count":4,"area":"agents"},{"id":"2606.02020","title":"Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning","created":"2026-06-01","cited_by_count":4,"area":"lr"},{"id":"2606.27359","title":"When are likely answers right? On Sequence Probability and Correctness in LLMs","created":"2026-06-25","cited_by_count":4,"area":null},{"id":"2509.09438","title":"GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models","created":"2025-09-11","cited_by_count":3,"area":"lr"},{"id":"2510.02919","title":"Self-Reflective Generation at Test Time","created":"2025-10-03","cited_by_count":3,"area":"lr"},{"id":"2510.13918","title":"Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling","created":"2025-10-15","cited_by_count":3,"area":"lr"},{"id":"2511.07318","title":"When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2511.11233","title":"STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models","created":"2025-11-14","cited_by_count":3,"area":"lr"},{"id":"2602.08948","title":"CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2605.03379","title":"Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference","created":"2026-05-05","cited_by_count":3,"area":"lr"},{"id":"2605.07654","title":"Reliable Chain-of-Thought via Prefix Consistency","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"id":"2608.19701","title":"Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration","created":"2026-08-20","cited_by_count":3,"area":null},{"id":"2509.05007","title":"Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework","created":"2025-09-05","cited_by_count":2,"area":"lr"},{"id":"2509.08016","title":"Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2509.19489","title":"Estimating the Self-Consistency of LLMs","created":"2025-09-23","cited_by_count":2,"area":"lr"},{"id":"2510.09535","title":"Mitigating Overthinking through Reasoning Shaping","created":"2025-10-10","cited_by_count":2,"area":"lr"},{"id":"2510.20690","title":"Neural Diversity Regularizes Hallucinations in Language Models","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2601.15690","title":"From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2602.01740","title":"MACD: Model-Aware Contrastive Decoding via Counterfactual Data","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.07725","title":"Verifiable Reasoning for LLM-based Generative Recommendation","created":"2026-03-08","cited_by_count":2,"area":"lr"},{"id":"2605.08070","title":"VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2606.04323","title":"Answer Self-Consistency with Margin-Triggered Question Re-Arbitration for the CVPR 2026 VidLLMs Challenge","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2505.11731","title":"Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.12452","title":"Missing vs. Unused Knowledge Hypothesis for Language Model Bottlenecks in Patent Understanding","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.18942","title":"Language Models Should be Used to Surface the Unwritten Code of Science and Society","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2601.05616","title":"Dual-Phase LLM Reasoning: Self-Evolved Mathematical Frameworks","created":"2026-01-09","cited_by_count":1,"area":"lr"},{"id":"2604.05539","title":"From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.05952","title":"Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration","created":"2026-04-07","cited_by_count":1,"area":"agents"},{"id":"2604.11025","title":"Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images","created":"2026-04-13","cited_by_count":1,"area":"lr"},{"id":"2604.20500","title":"Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.05592","title":"When Can Voting Help, Hurt, or Change Course? Exact Structure of Binary Test-Time Aggregation","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.13188","title":"LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.14098","title":"Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2606.01120","title":"Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.05054","title":"Boosting Self-Consistency with Ranking","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2606.13438","title":"CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency","created":"2026-06-11","cited_by_count":1,"area":"rag"},{"id":"2606.31484","title":"Fork-Think with Confidence","created":"2026-06-30","cited_by_count":1,"area":"lr"},{"id":"2608.14420","title":"More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2608.16425","title":"ParaTempo: Efficient Parallel Reasoning via Temporal Confidence","created":"2026-08-17","cited_by_count":1,"area":"lr"},{"id":"2504.05049","title":"CMaP-SAM: Contraction Mapping Prior for SAM-driven Few-shot Segmentation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2509.11295","title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2510.11104","title":"Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization","created":"2025-10-13","cited_by_count":0,"area":"lr"},{"id":"2512.00479","title":"Aligning Probabilistic Beliefs under Informative Missingness: LLM Steerability in Clinical Reasoning","created":"2025-11-29","cited_by_count":0,"area":"lr"},{"id":"2604.04418","title":"Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2604.05757","title":"Identifying Influential N-grams in Confidence Calibration via Regression Analysis","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2604.12491","title":"Calibrated Confidence Estimation for Tabular Question Answering","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.06219","title":"Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.08221","title":"NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.24384","title":"Side-by-side Comparison Amplifies Dialect Bias in Language Models","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.13591","title":"Confidence Composition for Multiagent Language Model Systems","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.20621","title":"PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2606.25552","title":"SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2607.15647","title":"Neuro-Symbolic AI for LEED compliance: Document-Centric Benchmarking, Deterministic Numeric Checking, and When Multimodal Hurts","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.20481","title":"Routing Without Training: Controllable-Ratio LLM Offloading via Reliability Gating","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2608.01207","title":"It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scaling","created":"2026-08-02","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}